Bhiksha Raj

TIST Journal 2026 Journal Article

Introduction to the Special Issue on Evaluations of Large Language Models Part 2

• Jindong Wang
• Linyi Yang
• Sunayana Sitaram
• Qiang Yang
• Bhiksha Raj

ICLR Conference 2025 Conference Paper

ADIFF: Explaining audio difference using natural language

• Soham Deshmukh
• Shuo Han
• Rita Singh
• Bhiksha Raj

Understanding and explaining differences between audio recordings is crucial for fields like audio forensics, quality assessment, and audio generation. This involves identifying and describing audio events, acoustic scenes, signal characteristics, and their emotional impact on listeners. This paper stands out as the first work to comprehensively study the task of explaining audio differences and then propose benchmark, baselines for the task. First, we present two new datasets for audio difference explanation derived from the AudioCaps and Clotho audio captioning datasets. Using Large Language Models (LLMs), we generate three levels of difference explanations: (1) concise descriptions of audio events and objects, (2) brief sentences about audio events, acoustic scenes, and signal properties, and (3) comprehensive explanations that include semantics and listener emotions. For the baseline, we use prefix tuning where audio embeddings from two audio files are used to prompt a frozen language model. Our empirical analysis and ablation studies reveal that the naive baseline struggles to distinguish perceptually similar sounds and generate detailed tier 3 explanations. To address these limitations, we propose ADIFF, which introduces a cross-projection module, position captioning, and a three-step training process to enhance the model’s ability to produce detailed explanations. We evaluate our model using objective metrics and human evaluation and show our model enhancements lead to significant improvements in performance over naive baseline and SoTA Audio-Language Model (ALM) Qwen Audio. Lastly, we conduct multiple ablation studies to study the effects of cross-projection, language model parameters, position captioning, third stage fine-tuning, and present our findings. Our benchmarks, findings, and strong baseline pave the way for nuanced and human-like explanations of audio differences.

AAAI Conference 2025 Conference Paper

Audio Entailment: Assessing Deductive Reasoning for Audio Understanding

• Soham Deshmukh
• Shuo Han
• Hazim Bukhari
• Benjamin Elizalde
• Hannes Gamper
• Rita Singh
• Bhiksha Raj

Recent literature uses language to build foundation models for audio. These Audio-Language Models (ALMs) are trained on a vast number of audio-text pairs and show remarkable performance in tasks including Text-to-Audio Retrieval, Captioning, and Question Answering. However, their ability to engage in more complex open-ended tasks, like Interactive Question-Answering, requires proficiency in logical reasoning- a skill not yet benchmarked. We introduce the novel task of Audio Entailment to evaluate an ALM's deductive reasoning ability. This task assesses whether a text description (hypothesis) of audio content can be deduced from an audio recording (premise), with potential conclusions being entailment, neutral, or contradiction, depending on the sufficiency of the evidence. We create two datasets for this task with audio recordings sourced from two audio captioning datasets-AudioCaps and Clotho-and hypotheses generated using Large Language Models (LLMs). We benchmark state-of-the-art ALMs and find deficiencies in logical reasoning with both zero-shot and linear probe evaluations. Finally, we propose "caption-before-reason", an intermediate step of captioning that improves the Zero-Shot and linear-probe performance of ALMs by an absolute 6% and 3%, respectively.

NeurIPS Conference 2025 Conference Paper

Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models

• Thanh-Dat Truong
• Huu-Thien Tran
• Tran Son
• Bhiksha Raj
• Khoa Luu

Large multimodal models (LMMs) have gained impressive performance due to their outstanding capability in various understanding tasks. However, these models still suffer from some fundamental limitations related to robustness and generalization due to the alignment and correlation between visual and textual features. In this paper, we introduce a simple but efficient learning mechanism for improving the robust alignment between visual and textual modalities by solving shuffling problems. In particular, the proposed approach can improve reasoning capability, visual understanding, and cross-modality alignment by introducing two new tasks: reconstructing the image order and the text order into the LMM's pre-training and fine-tuning phases. In addition, we propose a new directed-token approach to capture visual and textual knowledge, enabling the capability to reconstruct the correct order of visual inputs. Then, we introduce a new Image-to-Response Guided loss to further improve the visual understanding of the LMM in its responses. The proposed approach consistently achieves state-of-the-art (SoTA) performance compared with prior LMMs on academic task-oriented and instruction-following LMM benchmarks.

ICLR Conference 2025 Conference Paper

ImageFolder: Autoregressive Image Generation with Folded Tokens

• Xiang Li 0106
• Kai Qiu
• Hao Chen 0102
• Jason Kuen
• Jiuxiang Gu
• Bhiksha Raj
• Zhe Lin

Image tokenizers are crucial for visual generative models, \eg, diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approach to improve image reconstruction quality. However, tokenizers with longer token lengths are not guaranteed to achieve better generation quality. There exists a trade-off between reconstruction and generation quality regarding token length. In this paper, we investigate the impact of token length on both image reconstruction and generation and provide a flexible solution to the tradeoff. We propose \textbf{ImageFolder}, a semantic tokenizer that provides spatially aligned image tokens that can be folded during autoregressive modeling to improve both efficiency and quality. To enhance the representative capability without increasing token length, we leverage dual-branch product quantization to capture different contexts of images. Specifically, semantic regularization is introduced in one branch to encourage compacted semantic information while another branch is designed to capture pixel-level details. Extensive experiments demonstrate the superior quality of image generation and shorter token length with ImageFolder tokenizer.

TIST Journal 2025 Journal Article

Introduction to the Special Issue on Evaluations of Large Language Models: Part 1

• Jindong Wang
• Linyi Yang
• Sunayana Sitaram
• Qiang Yang
• Bhiksha Raj

ICML Conference 2025 Conference Paper

Masked Autoencoders Are Effective Tokenizers for Diffusion Models

• Hao Chen 0102
• Yujin Han
• Fangyi Chen
• Xiang Li 0106
• Yidong Wang 0003
• Jindong Wang 0001
• Ze Wang 0008
• Zicheng Liu 0001

Recent advances in latent diffusion models have demonstrated their effectiveness for high-resolution image synthesis. However, the properties of the latent space from tokenizer for better learning and generation of diffusion models remain under-explored. Theoretically and empirically, we find that improved generation quality is closely tied to the latent distributions with better structure, such as the ones with fewer Gaussian Mixture modes and more discriminative features. Motivated by these insights, we propose MAETok, an autoencoder (AE) leveraging mask modeling to learn semantically rich latent space while maintaining reconstruction fidelity. Extensive experiments validate our analysis, demonstrating that the variational form of autoencoders is not necessary, and a discriminative latent space from AE alone enables state-of-the-art performance on ImageNet generation using only 128 tokens. MAETok achieves significant practical improvements, enabling a gFID of 1. 69 with 76$\times$ faster training and 31$\times$ higher inference throughput for 512$\times$512 generation. Our findings show that the structure of the latent space, rather than variational constraints, is crucial for effective diffusion models. Code and trained models will be released.

NeurIPS Conference 2025 Conference Paper

Mellow: a small audio language model for reasoning

• Soham Deshmukh
• Satvik Dixit
• Rita Singh
• Bhiksha Raj

Multimodal Audio-Language Models (ALMs) can understand and reason over both audio and text. Typically, reasoning performance correlates with model size, with the best results achieved by models exceeding 8 billion parameters. However, no prior work has explored enabling small audio-language models to perform reasoning tasks, despite the potential applications for edge devices. To address this gap, we introduce Mellow, a small Audio-Language Model specifically designed for reasoning. Mellow achieves state-of-the-art performance among existing small audio-language models and surpasses several larger models in reasoning capabilities. For instance, Mellow scores 52. 11 on MMAU, comparable to SoTA Qwen2 Audio (which scores 52. 5) while using 50 times fewer parameters and being trained on 60 times less data (audio hrs). To train Mellow, we introduce ReasonAQA, a dataset designed to enhance audio-grounded reasoning in models. It consists of a mixture of existing datasets (30\% of the data) and synthetically generated data (70\%). The synthetic dataset is derived from audio captioning datasets, where Large Language Models (LLMs) generate detailed and multiple-choice questions focusing on audio events, objects, acoustic scenes, signal properties, semantics, and listener emotions. To evaluate Mellow’s reasoning ability, we benchmark it on a diverse set of tasks, assessing on both in-distribution and out-of-distribution data, including audio understanding, deductive reasoning, and comparative reasoning. Finally, we conduct extensive ablation studies to explore the impact of projection layer choices, synthetic data generation methods, and language model pretraining on reasoning performance. Our training dataset, findings, and baseline pave the way for developing small ALMs capable of reasoning.

NeurIPS Conference 2025 Conference Paper

On Fairness of Unified Multimodal Large Language Model for Image Generation

• Ming Liu
• Hao Chen
• Jindong Wang
• Liwen Wang
• Bhiksha Raj
• Wensheng Zhang

Unified multimodal large language models (U-MLLMs) have demonstrated impressive performance in end-to-end visual understanding and generation tasks. However, compared to generation-only systems (e. g. , Stable Diffusion), the unified architecture of U-MLLMs introduces new risks of propagating demographic stereotypes. In this paper, we benchmark several state-of-the-art U-MLLMs and show that they exhibit significant gender and race biases in the generated outputs. To diagnose the source of these biases, we propose a locate-then-fix framework: we first audit the vision and language components — using techniques such as linear probing and controlled generation — and find that the language model appears to be a primary origin of the observed generative bias. Moreover, we observe a ``partial alignment'' phenomenon, where the U-MLLMs exhibit less bias in understanding tasks yet produce substantially biased images. To address this, we introduce a novel \emph{balanced preference loss} that enforces uniform generation probabilities across demographics by leveraging a synthetically balanced dataset. Extensive experiments show that our approach significantly reduces demographic bias while preserving semantic fidelity and image quality. Our findings underscore the need for targeted debiasing strategies in unified multimodal systems and introduce a practical approach to mitigate biases.

ICLR Conference 2025 Conference Paper

Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video

• Xiaohao Xu
• Tianyi Zhang 0014
• Shibo Zhao
• Xiang Li 0106
• Sibo Wang
• Yongqi Chen
• Ye Li
• Bhiksha Raj

We aim to redefine robust ego-motion estimation and photorealistic 3D reconstruction by addressing a critical limitation: the reliance on noise-free data in existing models. While such sanitized conditions simplify evaluation, they fail to capture the unpredictable, noisy complexities of real-world environments. Dynamic motion, sensor imperfections, and synchronization perturbations lead to sharp performance declines when these models are deployed in practice, revealing an urgent need for frameworks that embrace and excel under real-world noise. To bridge this gap, we tackle three core challenges: scalable data generation, comprehensive benchmarking, and model robustness enhancement. First, we introduce a scalable noisy data synthesis pipeline that generates diverse datasets simulating complex motion, sensor imperfections, and synchronization errors. Second, we leverage this pipeline to create Robust-Ego3D, a benchmark rigorously designed to expose noise-induced performance degradation, highlighting the limitations of current learning-based methods in ego-motion accuracy and 3D reconstruction quality. Third, we propose Correspondence-guided Gaussian Splatting (CorrGS), a novel method that progressively refines an internal clean 3D representation by aligning noisy observations with rendered RGB-D frames from clean 3D map, enhancing geometric alignment and appearance restoration through visual correspondence. Extensive experiments on synthetic and real-world data demonstrate that CorrGS consistently outperforms prior state-of-the-art methods, particularly in scenarios involving rapid motion and dynamic illumination. We will release our code and benchmark to advance robust 3D vision, setting a new standard for ego-motion estimation and high-fidelity reconstruction in noisy environments.

ICLR Conference 2025 Conference Paper

Speech Robust Bench: A Robustness Benchmark For Speech Recognition

• Muhammad A. Shah
• David Solans Noguero
• Mikko A. Heikkilä
• Bhiksha Raj
• Nicolas Kourtellis

As Automatic Speech Recognition (ASR) models become ever more pervasive, it is important to ensure that they make reliable predictions under corruptions present in the physical and digital world. We propose Speech Robust Bench (SRB), a comprehensive benchmark for evaluating the robustness of ASR models to diverse corruptions. SRB is composed of 114 input perturbations which simulate an heterogeneous range of corruptions that ASR models may encounter when deployed in the wild. We use SRB to evaluate the robustness of several state-of-the-art ASR models and observe that model size and certain modeling choices such as the use of discrete representations, or self-training appear to be conducive to robustness. We extend this analysis to measure the robustness of ASR models on data from various demographic subgroups, namely English and Spanish speakers, and males and females. Our results revealed noticeable disparities in the model's robustness across subgroups. We believe that SRB will significantly facilitate future research towards robust ASR models, by making it easier to conduct comprehensive and comparable robustness evaluations.

ICLR Conference 2025 Conference Paper

Unsupervised Disentanglement of Content and Style via Variance-Invariance Constraints

• Yuxuan Wu
• Ziyu Wang 0008
• Bhiksha Raj
• Gus Xia

We contribute an unsupervised method that effectively learns disentangled content and style representations from sequences of observations. Unlike most disentanglement algorithms that rely on domain-specific labels or knowledge, our method is based on the insight of domain-general statistical differences between content and style --- content varies more among different fragments within a sample but maintains an invariant vocabulary across data samples, whereas style remains relatively invariant within a sample but exhibits more significant variation across different samples. We integrate such inductive bias into an encoder-decoder architecture and name our method after V3 (variance-versus-invariance). Experimental results show that V3 generalizes across multiple domains and modalities, successfully learning disentangled content and style representations, such as pitch and timbre from music audio, digit and color from images of hand-written digits, and action and character appearance from simple animations. V3 demonstrates strong disentanglement performance compared to existing unsupervised methods, along with superior out-of-distribution generalization and few-shot learning capabilities compared to supervised counterparts. Lastly, symbolic-level interpretability emerges in the learned content codebook, forging a near one-to-one alignment between machine representation and human knowledge.

ICML Conference 2024 Conference Paper

A General Framework for Learning from Weak Supervision

• Hao Chen 0102
• Jindong Wang 0001
• Lei Feng 0006
• Xiang Li 0106
• Yidong Wang 0003
• Xing Xie 0001
• Masashi Sugiyama
• Rita Singh

Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment. This paper introduces a general framework for learning from weak supervision (GLWS) with a novel algorithm. Central to GLWS is an Expectation-Maximization (EM) formulation, adeptly accommodating various weak supervision sources, including instance partial labels, aggregate statistics, pairwise observations, and unlabeled data. We further present an advanced algorithm that significantly simplifies the EM computational demands using a Non-deterministic Finite Automaton (NFA) along with a forward-backward algorithm, which effectively reduces time complexity from quadratic or factorial often required in existing solutions to linear scale. The problem of learning from arbitrary weak supervision is therefore converted to the NFA modeling of them. GLWS not only enhances the scalability of machine learning models but also demonstrates superior performance and versatility across 11 weak supervision scenarios. We hope our work paves the way for further advancements and practical deployment in this field.

ICML Conference 2024 Conference Paper

Completing Visual Objects via Bridging Generation and Segmentation

• Xiang Li 0106
• Yinpeng Chen
• Chung-Ching Lin
• Hao Chen 0102
• Kai Hu 0010
• Rita Singh
• Bhiksha Raj
• Lijuan Wang

This paper presents a novel approach to object completion, with the primary goal of reconstructing a complete object from its partially visible components. Our method, named MaskComp, delineates the completion process through iterative stages of generation and segmentation. In each iteration, the object mask is provided as an additional condition to boost image generation, and, in return, the generated images can lead to a more accurate mask by fusing the segmentation of images. We demonstrate that the combination of one generation and one segmentation stage effectively functions as a mask denoiser. Through alternation between the generation and segmentation stages, the partial object mask is progressively refined, providing precise shape guidance and yielding superior object completion results. Our experiments demonstrate the superiority of MaskComp over existing approaches, e. g. , ControlNet and Stable Diffusion, establishing it as an effective solution for object completion.

NeurIPS Conference 2024 Conference Paper

EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding

• Thanh-Dat Truong
• Utsav Prabhu
• Dongyi Wang
• Bhiksha Raj
• Susan Gauch
• Jeyamkondan Subbiah
• Khoa Luu

Unsupervised Domain Adaptation has been an efficient approach to transferring the semantic segmentation model across data distributions. Meanwhile, the recent Open-vocabulary Semantic Scene understanding based on large-scale vision language models is effective in open-set settings because it can learn diverse concepts and categories. However, these prior methods fail to generalize across different camera views due to the lack of cross-view geometric modeling. At present, there are limited studies analyzing cross-view learning. To address this problem, we introduce a novel Unsupervised Cross-view Adaptation Learning approach to modeling the geometric structural change across views in Semantic Scene Understanding. First, we introduce a novel Cross-view Geometric Constraint on Unpaired Data to model structural changes in images and segmentation masks across cameras. Second, we present a new Geodesic Flow-based Correlation Metric to efficiently measure the geometric structural changes across camera views. Third, we introduce a novel view-condition prompting mechanism to enhance the view-information modeling of the open-vocabulary segmentation network in cross-view adaptation learning. The experiments on different cross-view adaptation benchmarks have shown the effectiveness of our approach in cross-view modeling, demonstrating that we achieve State-of-the-Art (SOTA) performance compared to prior unsupervised domain adaptation and open-vocabulary semantic segmentation methods.

NeurIPS Conference 2024 Conference Paper

Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations

• Hao Chen
• Ankit Shah
• Jindong Wang
• Ran Tao
• Yidong Wang
• Xiang Li
• Xing Xie
• Masashi Sugiyama

Learning with reduced labeling standards, such as noisy label, partial label, and supplementary unlabeled data, which we generically refer to as imprecise label, is a commonplace challenge in machine learning tasks. Previous methods tend to propose specific designs for every emerging imprecise label configuration, which is usually unsustainable when multiple configurations of imprecision coexist. In this paper, we introduce imprecise label learning (ILL), a framework for the unification of learning with various imprecise label configurations. ILL leverages expectation-maximization (EM) for modeling the imprecise label information, treating the precise labels as latent variables. Instead of approximating the correct labels for training, it considers the entire distribution of all possible labeling entailed by the imprecise information. We demonstrate that ILL can seamlessly adapt to partial label learning, semi-supervised learning, noisy label learning, and, more importantly, a mixture of these settings, with closed-form learning objectives derived from the unified EM modeling. Notably, ILL surpasses the existing specified techniques for handling imprecise labels, marking the first practical and unified framework with robust and effective performance across various challenging settings. We hope our work will inspire further research on this topic, unleashing the full potential of ILL in wider scenarios where precise labels are expensive and complicated to obtain.

NeurIPS Conference 2024 Conference Paper

Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation

• Yizhou Zhao
• Hengwei Bian
• Kaihua Chen
• Pengliang Ji
• Liao Qu
• Shao-yu Lin
• Weichen Yu
• Haoran Li

Monocular depth estimation (MDE) is fundamental for deriving 3D scene structures from 2D images. While state-of-the-art monocular relative depth estimation (MRDE) excels in estimating relative depths for in-the-wild images, current monocular metric depth estimation (MMDE) approaches still face challenges in handling unseen scenes. Since MMDE can be viewed as the composition of MRDE and metric scale recovery, we attribute this difficulty to scene dependency, where MMDE models rely on scenes observed during supervised training for predicting scene scales during inference. To address this issue, we propose to use humans as landmarks for distilling scene-independent metric scale priors from generative painting models. Our approach, Metric from Human (MfH), bridges from generalizable MRDE to zero-shot MMDE in a generate-and-estimate manner. Specifically, MfH generates humans on the input image with generative painting and estimates human dimensions with an off-the-shelf human mesh recovery (HMR) model. Based on MRDE predictions, it propagates the metric information from painted humans to the contexts, resulting in metric depth estimations for the original input. Through this annotation-free test-time adaptation, MfH achieves superior zero-shot performance in MMDE, demonstrating its strong generalization ability.

NeurIPS Conference 2024 Conference Paper

Slight Corruption in Pre-training Data Makes Better Diffusion Models

• Hao Chen
• Yujin Han
• Diganta Misra
• Xiang Li
• Kai Hu
• Difan Zou
• Masashi Sugiyama
• Jindong Wang

Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on large-scale datasets, including web-crawled data with paired data and conditions, such as image-text and image-class pairs. Despite rigorous filtering, these pre-training datasets often inevitably contain corrupted pairs where conditions do not accurately describe the data. This paper presents the first comprehensive study on the impact of such corruption in pre-training data of DMs. We synthetically corrupt ImageNet-1K and CC3M to pre-train and evaluate over $50$ conditional DMs. Our empirical findings reveal that various types of slight corruption in pre-training can significantly enhance the quality, diversity, and fidelity of the generated images across different DMs, both during pre-training and downstream adaptation stages. Theoretically, we consider a Gaussian mixture model and prove that slight corruption in the condition leads to higher entropy and a reduced 2-Wasserstein distance to the ground truth of the data distribution generated by the corruptly trained DMs. Inspired by our analysis, we propose a simple method to improve the training of DMs on practical datasets by adding condition embedding perturbations (CEP). CEP significantly improves the performance of various DMs in both pre-training and downstream tasks. We hope that our study provides new insights into understanding the data and pre-training processes of DMs.

ICLR Conference 2024 Conference Paper

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks

• Hao Chen 0102
• Jindong Wang 0001
• Ankit Shah 0001
• Ran Tao 0013
• Hongxin Wei
• Xing Xie 0001
• Masashi Sugiyama
• Bhiksha Raj

Pre-training on large-scale datasets and then fine-tuning on downstream tasks have become a standard practice in deep learning. However, pre-training data often contain label noise that may adversely affect the generalization of the model. This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. More specifically, through extensive experiments of supervised pre-training models on synthetic noisy ImageNet-1K and YFCC15M datasets, we demonstrate that while slight noise in pre-training can benefit in-domain (ID) transfer performance, where the training and testing data share the same distribution, it always deteriorates out-of-domain (OOD) performance, where training and testing data distribution are different. We empirically verify that the reason behind is noise in pre-training shapes the feature space differently. We then propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization on both ID and OOD tasks, considering one may not be able to fully fine-tune or even access the pre-trained models. We conduct practical experiments on popular vision and language models that are pre-trained on noisy data for evaluation of our approach. Our analysis and results show the importance of this interesting and novel research direction, which we term Noisy Model Learning.

NeurIPS Conference 2023 Conference Paper

Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments

• Thanh-Dat Truong
• Hoang-Quan Nguyen
• Bhiksha Raj
• Khoa Luu

Continual semantic segmentation aims to learn new classes while maintaining the information from the previous classes. Although prior studies have shown impressive progress in recent years, the fairness concern in the continual semantic segmentation needs to be better addressed. Meanwhile, fairness is one of the most vital factors in deploying the deep learning model, especially in human-related or safety applications. In this paper, we present a novel Fairness Continual Learning approach to the semantic segmentation problem. In particular, under the fairness objective, a new fairness continual learning framework is proposed based on class distributions. Then, a novel Prototypical Contrastive Clustering loss is proposed to address the significant challenges in continual learning, i. e. , catastrophic forgetting and background shift. Our proposed loss has also been proven as a novel, generalized learning paradigm of knowledge distillation commonly used in continual learning. Moreover, the proposed Conditional Structural Consistency loss further regularized the structural constraint of the predicted segmentation. Our proposed approach has achieved State-of-the-Art performance on three standard scene understanding benchmarks, i. e. , ADE20K, Cityscapes, and Pascal VOC, and promoted the fairness of the segmentation model.

ICLR Conference 2023 Conference Paper

FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

• Yidong Wang 0003
• Hao Chen 0102
• Qiang Heng
• Wenxin Hou
• Yue Fan
• Zhen Wu 0002
• Jindong Wang 0001
• Marios Savvides

Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization. However, we argue that existing methods might fail to utilize the unlabeled data more effectively since they either use a pre-defined / fixed threshold or an ad-hoc threshold adjusting scheme, resulting in inferior performance and slow convergence. We first analyze a motivating example to obtain intuitions on the relationship between the desirable threshold and model's learning status. Based on the analysis, we hence propose FreeMatch to adjust the confidence threshold in a self-adaptive manner according to the model's learning status. We further introduce a self-adaptive class fairness regularization penalty to encourage the model for diverse predictions during the early training stage. Extensive experiments indicate the superiority of FreeMatch especially when the labeled data are extremely rare. FreeMatch achieves 5.78%, 13.59%, and 1.28% error rate reduction over the latest state-of-the-art method FlexMatch on CIFAR-10 with 1 label per class, STL-10 with 4 labels per class, and ImageNet with 100 labels per class, respectively. Moreover, FreeMatch can also boost the performance of imbalanced SSL. The codes can be found at https://github.com/microsoft/Semi-supervised-learning.

ICML Conference 2023 Conference Paper

How Many Perturbations Break This Model? Evaluating Robustness Beyond Adversarial Accuracy

• Raphaël Olivier
• Bhiksha Raj

Robustness to adversarial attacks is typically evaluated with adversarial accuracy. While essential, this metric does not capture all aspects of robustness and in particular leaves out the question of how many perturbations can be found for each point. In this work, we introduce an alternative approach, adversarial sparsity, which quantifies how difficult it is to find a successful perturbation given both an input point and a constraint on the direction of the perturbation. We show that sparsity provides valuable insight into neural networks in multiple ways: for instance, it illustrates important differences between current state-of-the-art robust models them that accuracy analysis does not, and suggests approaches for improving their robustness. When applying broken defenses effective against weak attacks but not strong ones, sparsity can discriminate between the totally ineffective and the partially effective defenses. Finally, with sparsity we can measure increases in robustness that do not affect accuracy: we show for example that data augmentation can by itself increase adversarial robustness, without using adversarial training.

NeurIPS Conference 2023 Conference Paper

PaintSeg: Painting Pixels for Training-free Segmentation

• Xiang Li
• Chung-Ching Lin
• Yinpeng Chen
• Zicheng Liu
• Jinglu Wang
• Rita Singh
• Bhiksha Raj

The paper introduces PaintSeg, a new unsupervised method for segmenting objects without any training. We propose an adversarial masked contrastive painting (AMCP) process, which creates a contrast between the original image and a painted image in which a masked area is painted using off-the-shelf generative models. During the painting process, inpainting and outpainting are alternated, with the former masking the foreground and filling in the background, and the latter masking the background while recovering the missing part of the foreground object. Inpainting and outpainting, also referred to as I-step and O-step, allow our method to gradually advance the target segmentation mask toward the ground truth without supervision or training. PaintSeg can be configured to work with a variety of prompts, e. g. coarse masks, boxes, scribbles, and points. Our experimental results demonstrate that PaintSeg outperforms existing approaches in coarse mask-prompt, box-prompt, and point-prompt segmentation tasks, providing a training-free solution suitable for unsupervised segmentation. Code: https: //github. com/lxa9867/PaintSeg.

AAAI Conference 2023 Conference Paper

Panoramic Video Salient Object Detection with Ambisonic Audio Guidance

• Xiang Li
• Haoyuan Cao
• Shijie Zhao
• Junlin Li
• Li Zhang
• Bhiksha Raj

Video salient object detection (VSOD), as a fundamental computer vision problem, has been extensively discussed in the last decade. However, all existing works focus on addressing the VSOD problem in 2D scenarios. With the rapid development of VR devices, panoramic videos have been a promising alternative to 2D videos to provide immersive feelings of the real world. In this paper, we aim to tackle the video salient object detection problem for panoramic videos, with their corresponding ambisonic audios. A multimodal fusion module equipped with two pseudo-siamese audio-visual context fusion (ACF) blocks is proposed to effectively conduct audio-visual interaction. The ACF block equipped with spherical positional encoding enables the fusion in the 3D context to capture the spatial correspondence between pixels and sound sources from the equirectangular frames and ambisonic audios. Experimental results verify the effectiveness of our proposed components and demonstrate that our method achieves state-of-the-art performance on the ASOD60K dataset.

ICLR Conference 2023 Conference Paper

SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning

• Hao Chen 0102
• Ran Tao 0013
• Yue Fan
• Yidong Wang 0003
• Jindong Wang 0001
• Bernt Schiele
• Xing Xie 0001
• Bhiksha Raj

The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling methods via a unified sample weighting formulation and demonstrate the inherent quantity-quality trade-off problem of pseudo-labeling with thresholding, which may prohibit learning. To this end, we propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training, effectively exploiting the unlabeled data. We derive a truncated Gaussian function to weight samples based on their confidence, which can be viewed as a soft version of the confidence threshold. We further enhance the utilization of weakly-learned classes by proposing a uniform alignment approach. In experiments, SoftMatch shows substantial improvements across a wide variety of benchmarks, including image, text, and imbalanced classification.

NeurIPS Conference 2023 Conference Paper

Training on Foveated Images Improves Robustness to Adversarial Attacks

• Muhammad Shah
• Aqsa Kashaf
• Bhiksha Raj

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks-- subtle, perceptually indistinguishable perturbations of inputs that change the response of the model. In the context of vision, we hypothesize that an important contributor to the robustness of human visual perception is constant exposure to low-fidelity visual stimuli in our peripheral vision. To investigate this hypothesis, we develop RBlur, an image transform that simulates the loss in fidelity of peripheral vision by blurring the image and reducing its color saturation based on the distance from a given fixation point. We show that compared to DNNs trained on the original images, DNNs trained on images transformed by RBlur are substantially more robust to adversarial attacks, as well as other, non-adversarial, corruptions, achieving up to 25% higher accuracy on perturbed data.

AAAI Conference 2023 Conference Paper

VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning

• Kashu Yamazaki
• Khoa Vo
• Quang Sang Truong
• Bhiksha Raj
• Ngan Le

Video Paragraph Captioning aims to generate a multi-sentence description of an untrimmed video with multiple temporal event locations in a coherent storytelling. Following the human perception process, where the scene is effectively understood by decomposing it into visual (e.g. human, animal) and non-visual components (e.g. action, relations) under the mutual influence of vision and language, we first propose a visual-linguistic (VL) feature. In the proposed VL feature, the scene is modeled by three modalities including (i) a global visual environment; (ii) local visual main agents; (iii) linguistic scene elements. We then introduce an autoregressive Transformer-in-Transformer (TinT) to simultaneously capture the semantic coherence of intra- and inter-event contents within a video. Finally, we present a new VL contrastive loss function to guarantee the learnt embedding features are consistent with the captions semantics. Comprehensive experiments and extensive ablation studies on the ActivityNet Captions and YouCookII datasets show that the proposed Visual-Linguistic Transformer-in-Transform (VLTinT) outperforms previous state-of-the-art methods in terms of accuracy and diversity. The source code is made publicly available at: https://github.com/UARK-AICV/VLTinT.

NeurIPS Conference 2023 Conference Paper

Weakly-Supervised Audio-Visual Segmentation

• Shentong Mo
• Bhiksha Raj

Audio-visual segmentation is a challenging task that aims to predict pixel-level masks for sound sources in a video. Previous work applied a comprehensive manually designed architecture with countless pixel-wise accurate masks as supervision. However, these pixel-level masks are expensive and not available in all cases. In this work, we aim to simplify the supervision as the instance-level annotation, $\textit{i. e. }$, weakly-supervised audio-visual segmentation. We present a novel Weakly-Supervised Audio-Visual Segmentation framework, namely WS-AVS, that can learn multi-scale audio-visual alignment with multi-scale multiple-instance contrastive learning for audio-visual segmentation. Extensive experiments on AVSBench demonstrate the effectiveness of our WS-AVS in the weakly-supervised audio-visual segmentation of single-source and multi-source scenarios.

ICLR Conference 2022 Conference Paper

SphereFace2: Binary Classification is All You Need for Deep Face Recognition

• Yandong Wen
• Weiyang Liu
• Adrian Weller
• Bhiksha Raj
• Rita Singh

State-of-the-art deep face recognition methods are mostly trained with a softmax-based multi-class classification framework. Despite being popular and effective, these methods still have a few shortcomings that limit empirical performance. In this paper, we start by identifying the discrepancy between training and evaluation in the existing multi-class classification framework and then discuss the potential limitations caused by the "competitive" nature of softmax normalization. Motivated by these limitations, we propose a novel binary classification training framework, termed SphereFace2. In contrast to existing methods, SphereFace2 circumvents the softmax normalization, as well as the corresponding closed-set assumption. This effectively bridges the gap between training and evaluation, enabling the representations to be improved individually by each binary classification task. Besides designing a specific well-performing loss function, we summarize a few general principles for this "one-vs-all" binary classification framework so that it can outperform current competitive methods. Our experiments on popular benchmarks demonstrate that SphereFace2 can consistently outperform state-of-the-art deep face recognition methods.

NeurIPS Conference 2022 Conference Paper

USB: A Unified Semi-supervised Learning Benchmark for Classification

• Yidong Wang
• Hao Chen
• Yue Fan
• Wang Sun
• Ran Tao
• Wenxin Hou
• Renjie Wang
• Linyi Yang

Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. To address the above issues, we construct a Unified SSL Benchmark (USB) for classification by selecting 15 diverse, challenging, and comprehensive tasks from CV, natural language processing (NLP), and audio processing (Audio), on which we systematically evaluate the dominant SSL methods, and also open-source a modular and extensible codebase for fair evaluation of these SSL methods. We further provide the pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning. USB enables the evaluation of a single SSL algorithm on more tasks from multiple domains but with less cost. Specifically, on a single NVIDIA V100, only 39 GPU days are required to evaluate FixMatch on 15 tasks in USB while 335 GPU days (279 GPU days on 4 CV datasets except for ImageNet) are needed on 5 CV tasks with TorchSSL.

NeurIPS Conference 2020 Conference Paper

Is normalization indispensable for training deep neural network?

• Jie Shao
• Kai Hu
• Changhu Wang
• Xiangyang Xue
• Bhiksha Raj

Normalization operations are widely used to train deep neural networks, and they can improve both convergence and generalization in most tasks. The theories for normalization's effectiveness and new forms of normalization have always been hot topics in research. To better understand normalization, one question can be whether normalization is indispensable for training deep neural network? In this paper, we study what would happen when normalization layers are removed from the network, and show how to train deep neural networks without normalization layers and without performance degradation. Our proposed method can achieve the same or even slightly better performance in a variety of tasks: image classification in ImageNet, object detection and segmentation in MS-COCO, video classification in Kinetics, and machine translation in WMT English-German, etc. Our study may help better understand the role of normalization layers and can be a competitive alternative to normalization layers. Codes are available.

NeurIPS Conference 2019 Conference Paper

Face Reconstruction from Voice using Generative Adversarial Networks

• Yandong Wen
• Bhiksha Raj
• Rita Singh

Voice profiling aims at inferring various human parameters from their speech, e. g. gender, age, etc. In this paper, we address the challenge posed by a subtask of voice profiling - reconstructing someone's face from their voice. The task is designed to answer the question: given an audio clip spoken by an unseen person, can we picture a face that has as many common elements, or associations as possible with the speaker, in terms of identity? To address this problem, we propose a simple but effective computational framework based on generative adversarial networks (GANs). The network learns to generate faces from voices by matching the identities of generated faces to those of the speakers, on a training set. We evaluate the performance of the network by leveraging a closely related task - cross-modal matching. The results show that our model is able to generate faces that match several biometric characteristics of the speaker, and results in matching accuracies that are much better than chance. The code is publicly available in https: //github. com/cmu-mlsp/reconstructing faces from_voices

IJCAI Conference 2019 Conference Paper

Learning Sound Events from Webly Labeled Data

• Anurag Kumar
• Ankit Shah
• Alexander Hauptmann
• Bhiksha Raj

In the last couple of years, weakly labeled learning has turned out to be an exciting approach for audio event detection. In this work, we introduce webly labeled learning for sound events which aims to remove human supervision altogether from the learning process. We first develop a method of obtaining labeled audio data from the web (albeit noisy), in which no manual labeling is involved. We then describe methods to efficiently learn from these webly labeled audio recordings. In our proposed system, WeblyNet, two deep neural networks co-teach each other to robustly learn from webly labeled data, leading to around 17% relative improvement over the baseline method. The method also involves transfer learning to obtain efficient representations.

JMLR Journal 2013 Journal Article

Greedy Sparsity-Constrained Optimization

• Sohail Bahmani
• Bhiksha Raj
• Petros T. Boufounos

Sparsity-constrained optimization has wide applicability in machine learning, statistics, and signal processing problems such as feature selection and Compressed Sensing. A vast body of work has studied the sparsity-constrained optimization from theoretical, algorithmic, and application aspects in the context of sparse estimation in linear models where the fidelity of the estimate is measured by the squared error. In contrast, relatively less effort has been made in the study of sparsity-constrained optimization in cases where nonlinear models are involved or the cost function is not quadratic. In this paper we propose a greedy algorithm, Gradient Support Pursuit (GraSP), to approximate sparse minima of cost functions of arbitrary form. Should a cost function have a Stable Restricted Hessian (SRH) or a Stable Restricted Linearization (SRL), both of which are introduced in this paper, our algorithm is guaranteed to produce a sparse vector within a bounded distance from the true sparse optimum. Our approach generalizes known results for quadratic cost functions that arise in sparse linear regression and Compressed Sensing. We also evaluate the performance of GraSP through numerical simulations on synthetic and real data, where the algorithm is employed for sparse logistic regression with and without l2-regularization. [abs] [ pdf ][ bib ] &copy JMLR 2013. ( edit, beta )

NeurIPS Conference 2012 Conference Paper

Unsupervised Structure Discovery for Semantic Analysis of Audio

• Sourish Chaudhuri
• Bhiksha Raj

Approaches to audio classification and retrieval tasks largely rely on detection-based discriminative models. We submit that such models make a simplistic assumption in mapping acoustics directly to semantics, whereas the actual process is likely more complex. We present a generative model that maps acoustics in a hierarchical manner to increasingly higher-level semantics. Our model has 2 layers with the first being generic sound units with no clear semantic associations, while the second layer attempts to find patterns over the generic sound units. We evaluate our model on a large-scale retrieval task from TRECVID 2011, and report significant improvements over standard baselines.

NeurIPS Conference 2010 Conference Paper

Multiparty Differential Privacy via Aggregation of Locally Trained Classifiers

• Manas Pathak
• Shantanu Rane
• Bhiksha Raj

As increasing amounts of sensitive personal information finds its way into data repositories, it is important to develop analysis mechanisms that can derive aggregate information from these repositories without revealing information about individual data instances. Though the differential privacy model provides a framework to analyze such mechanisms for databases belonging to a single party, this framework has not yet been considered in a multi-party setting. In this paper, we propose a privacy-preserving protocol for composing a differentially private aggregate classifier using classifiers trained locally by separate mutually untrusting parties. The protocol allows these parties to interact with an untrusted curator to construct additive shares of a perturbed aggregate classifier. We also present a detailed theoretical analysis containing a proof of differential privacy of the perturbed aggregate classifier and a bound on the excess risk introduced by the perturbation. We verify the bound with an experimental evaluation on a real dataset.

NeurIPS Conference 2009 Conference Paper

A Sparse Non-Parametric Approach for Single Channel Separation of Known Sounds

• Paris Smaragdis
• Madhusudana Shashanka
• Bhiksha Raj

In this paper we present an algorithm for separating mixed sounds from a monophonic recording. Our approach makes use of training data which allows us to learn representations of the types of sounds that compose the mixture. In contrast to popular methods that attempt to extract com- pact generalizable models for each sound from training data, we employ the training data itself as a representation of the sources in the mixture. We show that mixtures of known sounds can be described as sparse com- binations of the training data itself, and in doing so produce significantly better separation results as compared to similar systems based on compact statistical models.

NeurIPS Conference 2007 Conference Paper

Sparse Overcomplete Latent Variable Decomposition of Counts Data

• Madhusudana Shashanka
• Bhiksha Raj
• Paris Smaragdis

An important problem in many fields is the analysis of counts data to extract meaningful latent components. Methods like Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Allocation (LDA) have been proposed for this purpose. However, they are limited in the number of components they can extract and also do not have a provision to control the expressiveness" of the extracted components. In this paper, we present a learning formulation to address these limitations by employing the notion of sparsity. We start with the PLSA framework and use an entropic prior in a maximum a posteriori formulation to enforce sparsity. We show that this allows the extraction of overcomplete sets of latent components which better characterize the data. We present experimental evidence of the utility of such representations. "