Author name cluster

Yuhang He

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

16 papers

2 author rows

AAAI Conference 2026 Conference Paper

GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery

Jizhou Han
Chenhao Ding
Songlin Dong
Yuhang He
Shaokun Wang
Qiang Wang
Yihong Gong

Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamically, resulting in forgetting and inconsistent feature alignment. We propose GOAL, a unified framework that introduces a fixed Equiangular Tight Frame (ETF) classifier to impose a consistent geometric structure throughout learning. GOAL conducts supervised alignment for labeled samples and confidence-guided alignment for novel samples, enabling stable integration of new classes without disrupting old ones. Experiments on four benchmarks show that GOAL outperforms prior methods, reducing forgetting by 16.1% and boosting novel class discovery by 3.2%, establishing a strong solution for long-horizon continual discovery.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time Adaptation

Jianchao Zhao
Chenhao Ding
Songlin Dong
Jiangyang Li
Qiang Wang
Yuhang He
Yihong Gong

This paper focuses on the Continual Test-Time Adaptation (CTTA) task, aiming to enable an agent to continuously adapt to evolving target domains while retaining previously acquired domain knowledge for effective reuse when those domains reappear. Existing shared-parameter paradigms struggle to balance adaptation and forgetting, leading to decreased efficiency and stability. To address this, we propose a frequency-aware shared and self-adaptive expert framework, consisting of two key components: (i) a dual-branch expert architecture that extracts general features and dynamically models domain-specific representations, effectively reducing cross-domain interference and repetitive learning cost; and (ii) an online Frequency-aware Domain Discriminator (FDD), which leverages the robustness of low-frequency image signals for online domain shift detection, guiding dynamic allocation of expert resources for more stable and realistic adaptation. Additionally, we introduce a Continual Repeated Shifts (CRS) benchmark to simulate periodic domain changes for more realistic evaluation. Experimental results show that our method consistently outperforms existing approaches on both classification and segmentation CTTA tasks under standard and CRS settings, with ablations and visualizations confirming its effectiveness and robustness.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery

Jizhou Han
Shaokun Wang
Yuhang He
Chenhao Ding
Qiang Wang
Xinyuan Gao
Songlin Dong
Yihong Gong

Generalized Category Discovery (GCD) focuses on classifying known categories while simultaneously discovering novel categories from unlabeled data. However, previous GCD methods face challenges due to inconsistent optimization objectives and category confusion. This leads to feature overlap and ultimately hinders performance on novel categories. To address these issues, we propose the Neural Collapse-inspired Generalized Category Discovery (NC-GCD) framework. By pre-assigning and fixing Equiangular Tight Frame (ETF) prototypes, our method ensures an optimal geometric structure and a consistent optimization objective for both known and novel categories. We introduce a Consistent ETF Alignment Loss that unifies supervised and unsupervised ETF alignment and enhances category separability. Additionally, a Semantic Consistency Matcher (SCM) is designed to maintain stable and consistent label assignments across clustering iterations. Our method significantly enhancing novel category accuracy and demonstrating its effectiveness.

PDF Details

AAAI Conference 2025 Conference Paper

DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype

Qiang Wang
Yuhang He
Songlin Dong
Xiang Song
Jizhou Han
Haoyu Luo
Yihong Gong

Domain-Incremental Learning (DIL) enables vision models to adapt to changing conditions in real-world environments while maintaining the knowledge acquired from previous domains. Given privacy concerns and training time, Rehearsal-Free DIL (RFDIL) is more practical. Inspired by the incremental cognitive process of the human brain, we design Dual-level Concept Prototypes (DualCP) for each class to address the conflict between learning new knowledge and retaining old knowledge in RFDIL. To construct DualCP, we propose a Concept Prototype Generator (CPG) that generates both coarse-grained and fine-grained prototypes for each class. Additionally, we introduce a Coarse-to-Fine calibrator (C2F) to align image features with DualCP. Finally, we propose a Dual Dot-Regression (DDR) loss function to optimize our C2F module. Extensive experiments on the DomainNet, CDDB, and CORe50 datasets demonstrate the effectiveness of our method.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models

Xianda Guo
Ruijun Zhang
Yiqun Duan
Yuhang He
Dujun Nie
Wenke Huang
Chenming Zhang
Shuai Liu

Accurate spatial reasoning in outdoor environments—covering geometry, object pose, and inter-object relationships—is fundamental to downstream tasks such as mapping, motion forecasting, and high-level planning in autonomous driving. We introduce SURDS, a large-scale benchmark designed to systematically evaluate the spatial reasoning capabilities of vision language models (VLMs). Built on the nuScenes dataset, SURDS comprises 41, 080 vision–question–answer training instances and 9, 250 evaluation samples, spanning six spatial categories: orientation, depth estimation, pixel-level localization, pairwise distance, lateral ordering, and front–behind relations. We benchmark leading general-purpose VLMs, including GPT, Gemini, and Qwen, revealing persistent limitations in fine-grained spatial understanding. To address these deficiencies, we go beyond static evaluation and explore whether alignment techniques can improve spatial reasoning performance. Specifically, we propose a reinforcement learning–based alignment scheme leveraging spatially grounded reward signals—capturing both perception-level accuracy (location) and reasoning consistency (logic). We further incorporate final-answer correctness and output-format rewards to guide fine-grained policy adaptation. Our GRPO-aligned variant achieves overall score of 40. 80 in SURDS benchmark. Notably, it outperforms proprietary systems such as GPT-4o (13. 30) and Gemini-2. 0-flash (35. 71). To our best knowledge, this is the first study to demonstrate that reinforcement learning–based alignment can significantly and consistently enhance the spatial reasoning capabilities of VLMs in real-world driving contexts. We release the SURDS benchmark, evaluation toolkit, and GRPO alignment code through: https: //github. com/XiandaGuo/Drive-MLLM.

PDF Details

ICML Conference 2024 Conference Paper

Deep Neural Room Acoustics Primitive

Yuhang He
Anoop Cherian
Gordon Wichern
Andrew Markham

The primary objective of room acoustics is to model the intricate sound propagation dynamics from any source to receiver position within enclosed 3D spaces. These dynamics are encapsulated in the form of a 1D room impulse response (RIR). Precisely measuring RIR is difficult due to the complexity of sound propagation encompassing reflection, diffraction, and absorption. In this work, we propose to learn a continuous neural room acoustics field that implicitly encodes all essential sound propagation primitives for each enclosed 3D space, so that we can infer the RIR corresponding to arbitrary source-receiver positions unseen in the training dataset. Our framework, dubbed DeepNeRAP, is trained in a self-supervised manner without requiring direct access to RIR ground truth that is often needed in prior methods. The key idea is to design two cooperative acoustic agents to actively probe a 3D space, one emitting and the other receiving sound at various locations. Analyzing this sound helps to inversely characterize the acoustic primitives. Our framework is well-grounded in the fundamental physical principles of sound propagation, including reciprocity and globality, and thus is acoustically interpretable and meaningful. We present experiments on both synthetic and real-world datasets, demonstrating superior quality in RIR estimation against closely related methods.

Details

AAAI Conference 2024 Conference Paper

Evolving Parameterized Prompt Memory for Continual Learning

Muhammad Rifki Kurniawan
Xiang Song
Zhiheng Ma
Yuhang He
Yihong Gong
Yang Qi
Xing Wei

Recent studies have demonstrated the potency of leveraging prompts in Transformers for continual learning (CL). Nevertheless, employing a discrete key-prompt bottleneck can lead to selection mismatches and inappropriate prompt associations during testing. Furthermore, this approach hinders adaptive prompting due to the lack of shareability among nearly identical instances at more granular level. To address these challenges, we introduce the Evolving Parameterized Prompt Memory (EvoPrompt), a novel method involving adaptive and continuous prompting attached to pre-trained Vision Transformer (ViT), conditioned on specific instance. We formulate a continuous prompt function as a neural bottleneck and encode the collection of prompts on network weights. We establish a paired prompt memory system consisting of a stable reference and a flexible working prompt memory. Inspired by linear mode connectivity, we progressively fuse the working prompt memory and reference prompt memory during inter-task periods, resulting in continually evolved prompt memory. This fusion involves aligning functionally equivalent prompts using optimal transport and aggregating them in parameter space with an adjustable bias based on prompt node attribution. Additionally, to enhance backward compatibility, we propose compositional classifier initialization, which leverages prior prototypes from pre-trained models to guide the initialization of new classifiers in a subspace-aware manner. Comprehensive experiments validate that our approach achieves state-of-the-art performance in both class and domain incremental learning scenarios.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Non-exemplar Domain Incremental Object Detection via Learning Domain Bias

Xiang Song
Yuhang He
Songlin Dong
Yihong Gong

Domain incremental object detection (DIOD) aims to gradually learn a unified object detection model from a dataset stream composed of different domains, achieving good performance in all encountered domains. The most critical obstacle to this goal is the catastrophic forgetting problem, where the performance of the model improves rapidly in new domains but deteriorates sharply in old ones after a few sessions. To address this problem, we propose a non-exemplar DIOD method named learning domain bias (LDB), which learns domain bias independently at each new session, avoiding saving examples from old domains. Concretely, a base model is first obtained through training during session 1. Then, LDB freezes the weights of the base model and trains individual domain bias for each new incoming domain, adapting the base model to the distribution of new domains. At test time, since the domain ID is unknown, we propose a domain selector based on nearest mean classifier (NMC), which selects the most appropriate domain bias for a test image. Extensive experimental evaluations on two series of datasets demonstrate the effectiveness of the proposed LDB method in achieving high accuracy on new and old domain datasets. The code is available at https://github.com/SONGX1997/LDB.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models

Cong Wan
Yuhang He
Xiang Song
Yihong Gong

Diffusion models have revolutionized customized text-to-image generation, allowing for efficient synthesis of photos from personal data with textual descriptions. However, these advancements bring forth risks including privacy breaches and unauthorized replication of artworks. Previous researches primarily center around using “prompt-specific methods” to generate adversarial examples to protect personal images, yet the effectiveness of existing methods is hindered by constrained adaptability to different prompts. In this paper, we introduce a Prompt-Agnostic Adversarial Perturbation (PAP) method for customized diffusion models. PAP first models the prompt distribution using a Laplace Approximation, and then produces prompt-agnostic perturbations by maximizing a disturbance expectation based on the modeled distribution. This approach effectively tackles the prompt-agnostic attacks, leading to improved defense stability. Extensive experiments in face privacy and artistic style protection, demonstrate the superior generalization of our method in comparison to existing techniques.

PDF Details DOI

AAAI Conference 2024 Conference Paper

SoundCount: Sound Counting from Raw Audio with Dyadic Decomposition Neural Network

Yuhang He
Zhuangzhuang Dai
Niki Trigoni
Long Chen
Andrew Markham

In this paper, we study an underexplored, yet important and challenging problem: counting the number of distinct sounds in raw audio characterized by a high degree of polyphonicity. We do so by systematically proposing a novel end-to-end trainable neural network~(which we call DyDecNet, consisting of a dyadic decomposition front-end and backbone network), and quantifying the difficulty level of counting depending on sound polyphonicity. The dyadic decomposition front-end progressively decomposes the raw waveform dyadically along the frequency axis to obtain time-frequency representation in multi-stage, coarse-to-fine manner. Each intermediate waveform convolved by a parent filter is further processed by a pair of child filters that evenly split the parent filter's carried frequency response, with the higher-half child filter encoding the detail and lower-half child filter encoding the approximation. We further introduce an energy gain normalization to normalize sound loudness variance and spectrum overlap, and apply it to each intermediate parent waveform before feeding it to the two child filters. To better quantify sound counting difficulty level, we further design three polyphony-aware metrics: polyphony ratio, max polyphony and mean polyphony. We test DyDecNet on various datasets to show its superiority, and we further show dyadic decomposition network can be used as a general front-end to tackle other acoustic tasks.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Towards Learning Group-Equivariant Features for Domain Adaptive 3D Detection

Sangyun Shin
Yuhang He
Madhu Vankadari
Ta-Ying Cheng
Qian Xie
Andrew Markham
Niki Trigoni

The performance of 3D object detection in large outdoor point clouds deteriorates significantly in an unseen environment due to the inter-domain gap. To address these challenges, most existing methods for domain adaptation harness self-training schemes and attempt to bridge the gap by focusing on a single factor that causes the inter-domain gap, such as objects' sizes, shapes, and foreground density variation. However, the resulting adaptations suggest that there is still a substantial inter-domain gap left to be minimized. We argue that this is due to two limitations: 1) Biased pseudo-label collection from self-training. 2) Multiple factors jointly contributing to how the object is perceived in the unseen target domain. In this work, we propose a grouping-exploration strategy framework, Group Explorer Domain Adaptation ($\textbf{GroupEXP-DA}$), to addresses those two issues. Specifically, our grouping divides the available label sets into multiple clusters and ensures all of them have equal learning attention with the group-equivariant spatial feature, avoiding dominant types of objects causing imbalance problems. Moreover, grouping learns to divide objects by considering inherent factors in a data-driven manner, without considering each factor separately as existing works. On top of the group-equivariant spatial feature that selectively detects objects similar to the input group, we additionally introduce an explorative group update strategy that reduces the false negative detection in the target domain, further reducing the inter-domain gap. During inference, only the learned group features are necessary for making the group-equivariant spatial feature, placing our method as a simple add-on that can be applicable to most existing detectors. We show how each module contributes to substantially bridging the inter-domain gaps compared to existing works across large urban outdoor datasets such as NuScenes, Waymo, and KITTI.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation

Jia-Xing Zhong
Ta-Ying Cheng
Yuhang He
Kai Lu
Kaichen Zhou
Andrew Markham
Niki Trigoni

A truly generalizable approach to rigid segmentation and motion estimation is fundamental to 3D understanding of articulated objects and moving scenes. In view of the closely intertwined relationship between segmentation and motion estimates, we present an SE(3) equivariant architecture and a training strategy to tackle this task in an unsupervised manner. Our architecture is composed of two interconnected, lightweight heads. These heads predict segmentation masks using point-level invariant features and estimate motion from SE(3) equivariant features, all without the need for category information. Our training strategy is unified and can be implemented online, which jointly optimizes the predicted segmentation and motion by leveraging the interrelationships among scene flow, segmentation mask, and rigid transformations. We conduct experiments on four datasets to demonstrate the superiority of our method. The results show that our method excels in both model performance and computational efficiency, with only 0. 25M parameters and 0. 92G FLOPs. To the best of our knowledge, this is the first work designed for category-agnostic part-level SE(3) equivariance in dynamic point clouds.

PDF Details

AAAI Conference 2021 Conference Paper

Error-Aware Density Isomorphism Reconstruction for Unsupervised Cross-Domain Crowd Counting

Yuhang He
Zhiheng Ma
Xing Wei
Xiaopeng Hong
Wei Ke
Yihong Gong

This paper focuses on the unsupervised domain adaptation problem for video-based crowd counting, in which we use labeled data as source domain and unlabelled video data as target domain. It is challenging as there is a huge gap between the source and the target domain and no annotations of samples are available in the target domain. The key issue is how to utilize unlabelled videos in the target domain for knowledge learning and transferring from the source domain. To tackle this problem, we propose a novel Error-aware Density Isomorphism REConstruction Network (EDIREC-Net) for cross-domain crowd counting. EDIREC-Net jointly transfers a pre-trained counting model to target domains using a density isomorphism reconstruction objective and models the reconstruction erroneousness by error reasoning. Specifically, as crowd flows in videos are consecutive, the density maps in adjacent frames turn out to be isomorphic. On this basis, we regard the density isomorphism reconstruction error as a self-supervised signal to transfer the pre-trained counting models to different target domains. Moreover, we leverage an estimation-reconstruction consistency to monitor the density reconstruction erroneousness and suppress unreliable density reconstructions during training. Experimental results on four benchmark datasets demonstrate the superiority of the proposed method and ablation studies investigate the efficiency and robustness. The source code is available at https: //github. com/GehenHe/EDIREC-Net.

PDF Details

ICML Conference 2021 Conference Paper

SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform

Yuhang He
Niki Trigoni
Andrew Markham

We present a new framework SoundDet, which is an end-to-end trainable and light-weight framework, for polyphonic moving sound event detection and localization. Prior methods typically approach this problem by preprocessing raw waveform into time-frequency representations, which is more amenable to process with well-established image processing pipelines. Prior methods also detect in segment-wise manner, leading to incomplete and partial detections. SoundDet takes a novel approach and directly consumes the raw, multichannel waveform and treats the spatio-temporal sound event as a complete “sound-object" to be detected. Specifically, SoundDet consists of a backbone neural network and two parallel heads for temporal detection and spatial localization, respectively. Given the large sampling rate of raw waveform, the backbone network first learns a set of phase-sensitive and frequency-selective bank of filters to explicitly retain direction-of-arrival information, whilst being highly computationally and parametrically efficient than standard 1D/2D convolution. A dense sound event proposal map is then constructed to handle the challenges of predicting events with large varying temporal duration. Accompanying the dense proposal map are a temporal overlapness map and a motion smoothness map that measure a proposal’s confidence to be an event from temporal detection accuracy and movement consistency perspective. Involving the two maps guarantees SoundDet to be trained in a spatio-temporally unified manner. Experimental results on the public DCASE dataset show the advantage of SoundDet on both segment-based evaluation and our newly proposed event-based evaluation system.

Details

ICRA Conference 2019 Conference Paper

Real-Time Vehicle Detection from Short-range Aerial Image with Compressed MobileNet

Yuhang He
Ziyu Pan
Lingxi Li 0001
Yunxiao Shan
Dongpu Cao
Long Chen 0005

Vehicle detection from short-range aerial image faces challenges including vehicle blocking, irrelevant object interference, motion blurring, color variation etc. , leading to the difficulty to achieve high detection accuracy and real-time detection speed. In this paper, benefiting from the recent development in MobileNet family network engineering, we propose a compressed MobileNet which is not only internally resistant to the above listed challenges but also gains the best detection accuracy/speed tradeoff when comparing with the original MobileNet. In a nutshell, we reduce the bottleneck architecture number during the feature map downsampling stage but add more bottlenecks during the feature map plateau stage, neither extra FLOPs nor parameters are thus involved but reduced inference time and better accuracy are expected. We conduct experiment on our collected 5-k short-range aerial images, containing six vehicle categories: truck, car, bus, bicycle, motorcycle, crowded bicycles and crowded motorcycles. Our proposed compressed MobileNet achieves 110 FPS (GPU), 31 FPS (CPU) and 15 FPS (mobile phone), 1. 2 times faster and 2% more accurate (mAP) than the original MobileNet.

Details

AAAI Conference 2018 Conference Paper

Dress Fashionably: Learn Fashion Collocation With Deep Mixed-Category Metric Learning

Long Chen
Yuhang He

In this paper, we seek to enable machine to answer questions like, given a clutch bag, what kind of skirt, heel and even accessory best fashionably collocate with it? This problem, dubbed fashion collocation, has almost been neglected by researchers due to the large uncertainty lies in fashion collocation and professional expertise required to address it. In this paper, we narrow down the well-collocated samples to be fashion images shared on fashion websites, with which we propose an end-to-end trainable deep mixed-category metric learning method to project well-collocated clothing items to lie close but items violating well-collocation far apart in the deep embedding space. Speciﬁcally, we simultaneously model the intra-category exclusiveness and cross-category inclusiveness of fashion collocation by feeding a set of wellcollocated clothing items and corresponding bad-collocated clothing items to the deep neural network, further a hardaware online exemplar mining strategy is designed to force the whole neural network to be trainable and learn discriminative features at the early and later training stages respectively. To motivate more research in fashion collocation, we collect a dataset of 0. 2 million fashionably well-collocated images consisting of either on-body or off-body clothing items or accessories. Extensive experimental results show the feasibility and superiority of our method.

PDF Details