Author name cluster

Henghui Ding

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.

22 papers

2 author rows

AAAI Conference 2026 Conference Paper

AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios

Chenglizhao Chen
Shaofeng Liang
Runwei Guan
Xiaolou Sun
Haocheng Zhao
Haiyun Jiang
Tao Huang
Henghui Ding

Referring Multi-Object Tracking (RMOT) aims to achieve precise object detection and tracking through natural language instructions, representing a fundamental capability for intelligent robotic systems. However, current RMOT research remains mostly confined to ground-level scenarios, which constrains their ability to capture broad-scale scene contexts and perform comprehensive tracking and path planning. In contrast, Unmanned Aerial Vehicles (UAVs) leverage their expansive aerial perspectives and superior maneuverability to enable wide-area surveillance. Moreover, UAVs have emerged as critical platforms for Embodied Intelligence, which has given rise to an unprecedented demand for intelligent aerial systems capable of natural language interaction. To this end, we introduce AerialMind, the first large-scale RMOT benchmark in UAV scenarios, which aims to bridge this research gap. To facilitate its construction, we develop an innovative semi-automated collaborative agent-based labeling assistant (COALA) framework that significantly reduces labor costs while maintaining annotation quality. Furthermore, we propose HawkEyeTrack (HETrack), a novel method that collaboratively enhances vision-language representation learning and improves the perception of UAV scenarios. Comprehensive experiments validated the challenging nature of our dataset and the effectiveness of our method.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Free-Form Scene Editor: Enabling Multi-Round Object Manipulation Like in a 3D Engine

Xincheng Shuai
Zhenyuan Qin
Henghui Ding
Dacheng Tao

Recent advances in text-to-image (T2I) diffusion models have significantly improved semantic image editing, yet most methods fall short in performing 3D-aware object manipulation. In this work, we present FFSE, a 3D-aware autoregressive framework designed to enable intuitive, physically-consistent object editing directly on real-world images. Unlike previous approaches that either operate in image space or require slow and error-prone 3D reconstruction, FFSE models editing as a sequence of learned 3D transformations, allowing users to perform arbitrary manipulations, such as translation, scaling, and rotation, while preserving realistic background effects (e.g., shadows, reflections) and maintaining global scene consistency across multiple editing rounds. To support learning of multi-round 3D-aware object manipulation, we introduce 3DObjectEditor, a hybrid dataset constructed from simulated editing sequences across diverse objects and scenes, enabling effective training under multi-round and dynamic conditions. Extensive experiments show that the proposed FFSE significantly outperforms existing methods in both single-round and multi-round 3D-aware editing scenarios.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Segment Anything Across Shots: A Method and Benchmark

Hengrui Hu
Kaining Ying
Henghui Ding

This work focuses on multi-shot semi-supervised video object segmentation (MVOS), which aims at segmenting the target object indicated by an initial mask throughout a video with multiple shots. While existing VOS methods mainly focus on single-shot videos, they often fail to handle shot discontinuities, thereby limiting their real-world applicability. Furthermore, the lack of annotated multi-shot data poses a major challenge for MVOS research. To address these issues, we propose a transition mimicking data augmentation strategy (TMA) that enables cross-shot generalization using single-shot data, and a transition-aware method, Segment Anything Across Shots (SAAS), which detects and comprehends shot transitions during inference. To support evaluation and future study in MVOS, we introduce Cut-VOS, a new MVOS benchmark with dense mask annotations, diverse object categories, and high-frequency transitions. Extensive experiments on YouMVOS and Cut-VOS demonstrate that the proposed SAAS achieves state-of-the-art performance by effectively mimicking, understanding, and segmenting across complex transitions.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Explore In-Context Segmentation via Latent Diffusion Models

Chaoyang Wang
Xiangtai Li
Henghui Ding
Lu Qi
Jiangning Zhang
Yunhai Tong
Chen Change Loy
Shuicheng Yan

In-context segmentation has drawn increasing attention with the advent of vision foundation models. Its goal is to segment objects using given reference images. Most existing approaches adopt metric learning or masked image modeling to build the correlation between visual prompts and input image queries. This work approaches the problem from a fresh perspective - unlocking the capability of the latent diffusion model (LDM) for in-context segmentation and investigating different design choices. Specifically, we examine the problem from three angles: instruction extraction, output alignment, and meta-architectures. We design a two-stage masking strategy to prevent interfering information from leaking into the instructions. In addition, we propose an augmented pseudo-masking target to ensure the model predicts without forgetting the original images. Moreover, we build a new and fair in-context segmentation benchmark that covers both image and video datasets. Experiments validate the effectiveness of our approach, demonstrating comparable or even stronger results than previous specialist or visual foundation models. We hope our work inspires others to rethink the unification of segmentation and generation.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension

Yaxian Wang
Henghui Ding
Shuting He
Xudong Jiang
Bifan Wei
Jun Liu

In this work, we address the challenging task of Generalized Referring Expression Comprehension (GREC). Compared to the classic Referring Expression Comprehension (REC) that focuses on single-target expressions, GREC extends the scope to a more practical setting by further encompassing no-target and multi-target expressions. Existing REC methods face challenges in handling the complex cases encountered in GREC, primarily due to their fixed output and limitations in multi-modal representations. To address these issues, we propose a Hierarchical Alignment-enhanced Adaptive Grounding Network (HieA2G) for GREC, which can flexibly deal with various types of referring expressions. First, a Hierarchical Multi-modal Semantic Alignment (HMSA) module is proposed to incorporate three levels of alignments, including word-object, phrase-object, and text-image alignment. It enables hierarchical cross-modal interactions across multiple levels to achieve comprehensive and robust multi-modal understanding, greatly enhancing grounding ability for complex cases. Then, to address the varying number of target objects in GREC, we introduce an Adaptive Grounding Counter (AGC) to dynamically determine the number of output targets. Additionally, an auxiliary contrastive loss is employed in AGC to enhance object-counting ability by pulling in multi-modal features with the same counting and pushing away those with different counting. Extensive experimental results show that HieA2G achieves new state-of-the-art performance on the challenging GREC task and also the other 4 tasks, including REC, Phrase Grounding, Referring Expression Segmentation (RES), and Generalized Referring Expression Segmentation (GRES), demonstrating the remarkable superiority and generalizability of the proposed HieA2G.

PDF Details DOI

AAAI Conference 2025 Conference Paper

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

Xuan Shen
Zhao Song
Yufa Zhou
Bo Chen
Yanyu Li
Yifan Gong
Kai Zhang
Hao Tan

Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The promising results come at the cost of slow inference, as each denoising step requires running the whole transformer model with a large amount of parameters. In this paper, we show that performing the full computation of the model at each diffusion step is unnecessary, as some computations can be skipped by lazily reusing the results of previous steps. Furthermore, we show that the lower bound of similarity between outputs at consecutive steps is notably high, and this similarity can be linearly approximated using the inputs. To verify our demonstrations, we propose the **LazyDiT**, a lazy learning framework that efficiently leverages cached results from earlier steps to skip redundant computations. Specifically, we incorporate lazy learning layers into the model, effectively trained to maximize laziness, enabling dynamic skipping of redundant computations. Experimental results show that LazyDiT outperforms the DDIM sampler across multiple diffusion transformer models at various resolutions. Furthermore, we implement our method on mobile devices, achieving better performance than DDIM with similar latency.

PDF Details DOI

ICML Conference 2025 Conference Paper

ReferSplat: Referring Segmentation in 3D Gaussian Splatting

Shuting He
Guangquan Jie
Changshuo Wang 0001
Yun Zhou
Shuming Hu
Guanbin Li
Henghui Ding

We introduce Referring 3D Gaussian Splatting Segmentation (R3DGS), a new task that aims to segment target objects in a 3D Gaussian scene based on natural language descriptions, which often contain spatial relationships or object attributes. This task requires the model to identify newly described objects that may be occluded or not directly visible in a novel view, posing a significant challenge for 3D multi-modal understanding. Developing this capability is crucial for advancing embodied AI. To support research in this area, we construct the first R3DGS dataset, Ref-LERF. Our analysis reveals that 3D multi-modal understanding and spatial relationship modeling are key challenges for R3DGS. To address these challenges, we propose ReferSplat, a framework that explicitly models 3D Gaussian points with natural language expressions in a spatially aware paradigm. ReferSplat achieves state-of-the-art performance on both the newly proposed R3DGS task and 3D open-vocabulary segmentation benchmarks. Dataset and code are available at https: //github. com/heshuting555/ReferSplat.

Details

NeurIPS Conference 2025 Conference Paper

SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models

Ye Sun
Hao Zhang
Henghui Ding
Tiehua Zhang
Xingjun Ma
Yu-Gang Jiang

Achieving fine-grained spatio-temporal understanding in videos remains a major challenge for current Video Large Multimodal Models (Video LMMs). Addressing this challenge requires mastering two core capabilities: video referring understanding, which captures the semantics of video regions, and video grounding, which segments object regions based on natural language descriptions. However, most existing approaches tackle these tasks in isolation, limiting progress toward unified, referentially grounded video interaction. We identify a key bottleneck in the lack of high-quality, unified video instruction data and a comprehensive benchmark for evaluating referentially grounded video chat. To address these challenges, we contribute in three core aspects: dataset, model, and benchmark. First, we introduce SAMA-239K, a large-scale dataset comprising 15K videos specifically curated to enable joint learning of video referring understanding, grounding, and multi-turn video chat. Second, we propose the SAMA model, which incorporates a versatile spatio-temporal context aggregator and a Segment Anything Model to jointly enhance fine-grained video comprehension and precise grounding capabilities. Finally, we establish SAMA-Bench, a meticulously designed benchmark consisting of 5, 067 questions from 522 videos, to comprehensively evaluate the integrated capabilities of Video LMMs in multi-turn, spatio-temporal referring understanding and grounded dialogue. Extensive experiments and benchmarking results show that SAMA not only achieves strong performance on SAMA-Bench but also sets a new state-of-the-art on general grounding benchmarks, while maintaining highly competitive performance on standard visual understanding benchmarks.

PDF Details

NeurIPS Conference 2025 Conference Paper

SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation

Zhenyuan Qin
Xincheng Shuai
Henghui Ding

Controllable image generation has attracted increasing attention in recent years, enabling users to manipulate visual content such as identity and style. However, achieving simultaneous control over the 9D poses (location, size, and orientation) of multiple objects remains an open challenge. Despite recent progress, existing methods often suffer from limited controllability and degraded quality, falling short of comprehensive multi-object 9D pose control. To address these limitations, we propose SceneDesigner, a method for accurate and flexible multi-object 9-DoF pose manipulation. SceneDesigner incorporates a branched network to the pre-trained base model and leverages a new representation, CNOCS map, which encodes 9D pose information from the camera view. This representation exhibits strong geometric interpretation properties, leading to more efficient and stable training. To support training, we construct a new dataset, ObjectPose9D, which aggregates images from diverse sources along with 9D pose annotations. To further address data imbalance issues, particularly performance degradation on low-frequency poses, we introduce a two-stage training strategy with reinforcement learning, where the second stage fine-tunes the model using a reward-based objective on rebalanced data. At inference time, we propose Disentangled Object Sampling, a technique that mitigates insufficient object generation and concept confusion in complex multi-object scenes. Moreover, by integrating user-specific personalization weights, SceneDesigner enables customized pose control for reference subjects. Extensive qualitative and quantitative experiments demonstrate that SceneDesigner significantly outperforms existing approaches in both controllability and quality.

PDF Details

ICLR Conference 2024 Conference Paper

Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment

Li Siyao
Tianpei Gu
Zhitao Yang
Zhengyu Lin
Ziwei Liu 0002
Henghui Ding
Lei Yang 0059
Chen Change Loy

We introduce a novel task within the field of human motion generation, termed dance accompaniment, which necessitates the generation of responsive movements from a dance partner, the "follower", synchronized with the lead dancer’s movements and the underlying musical rhythm. Unlike existing solo or group dance generation tasks, a duet dance scenario entails a heightened degree of interaction between the two participants, requiring delicate coordination in both pose and position. To support this task, we first build a large-scale and diverse duet interactive dance dataset, DD100, by recording about 117 minutes of professional dancers’ performances. To address the challenges inherent in this task, we propose a GPT based model, Duolando, which autoregressively predicts the subsequent tokenized motion conditioned on the coordinated information of the music, the leader’s and the follower’s movements. To further enhance the GPT’s capabilities of generating stable results on unseen conditions (music and leader motions), we devise an off-policy reinforcement learning strategy that allows the model to explore viable trajectories from out-of-distribution samplings, guided by human-defined rewards. Based on the collected dataset and proposed method, we establish a benchmark with several carefully designed metrics.

Details

NeurIPS Conference 2024 Conference Paper

How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?

Jiahua Dong
Wenqi Liang
Hongliu Li
Duzhen Zhang
Meng Cao
Henghui Ding
Salman Khan
Fahad S. Khan

Custom diffusion models (CDMs) have attracted widespread attention due to their astonishing generative ability for personalized concepts. However, most existing CDMs unreasonably assume that personalized concepts are fixed and cannot change over time. Moreover, they heavily suffer from catastrophic forgetting and concept neglect on old personalized concepts when continually learning a series of new concepts. To address these challenges, we propose a novel Concept-Incremental text-to-image Diffusion Model (CIDM), which can resolve catastrophic forgetting and concept neglect to learn new customization tasks in a concept-incremental manner. Specifically, to surmount the catastrophic forgetting of old concepts, we develop a concept consolidation loss and an elastic weight aggregation module. They can explore task-specific and task-shared knowledge during training, and aggregate all low-rank weights of old concepts based on their contributions during inference. Moreover, in order to address concept neglect, we devise a context-controllable synthesis strategy that leverages expressive region features and noise estimation to control the contexts of generated images according to user conditions. Experiments validate that our CIDM surpasses existing custom diffusion models. The source codes are available at https: //github. com/JiahuaDong/CIFC.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing

Song Xia
Yi Yu 0011
Xudong Jiang 0001
Henghui Ding

Randomized Smoothing (RS) has been proven a promising method for endowing an arbitrary image classifier with certified robustness. However, the substantial uncertainty inherent in the high-dimensional isotropic Gaussian noise imposes the curse of dimensionality on RS. Specifically, the upper bound of ${\ell_2}$ certified robustness radius provided by RS exhibits a diminishing trend with the expansion of the input dimension $d$, proportionally decreasing at a rate of $1/\sqrt{d}$. This paper explores the feasibility of providing ${\ell_2}$ certified robustness for high-dimensional input through the utilization of dual smoothing in the lower-dimensional space. The proposed Dual Randomized Smoothing (DRS) down-samples the input image into two sub-images and smooths the two sub-images in lower dimensions. Theoretically, we prove that DRS guarantees a tight ${\ell_2}$ certified robustness radius for the original input and reveal that DRS attains a superior upper bound on the ${\ell_2}$ robustness radius, which decreases proportionally at a rate of $(1/\sqrt m + 1/\sqrt n )$ with $m+n=d$. Extensive experiments demonstrate the generalizability and effectiveness of DRS, which exhibits a notable capability to integrate with established methodologies, yielding substantial improvements in both accuracy and ${\ell_2}$ certified robustness baselines of RS on the CIFAR-10 and ImageNet datasets. Code is available at https://github.com/xiasong0501/DRS.

Details

AAAI Conference 2024 Conference Paper

PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification

Xinke Li
Junchi Lu
Henghui Ding
Changsheng Sun
Joey Tianyi Zhou
Yeow Meng Chee

With the growth of 3D sensing technology, the deep learning system for 3D point clouds has become increasingly important, especially in applications such as autonomous vehicles where safety is a primary concern. However, there are growing concerns about the reliability of these systems when they encounter noisy point clouds, either occurring naturally or introduced with malicious intent. This paper highlights the challenges of point cloud classification posed by various forms of noise, from simple background noise to malicious adversarial/backdoor attacks that can intentionally skew model predictions. While there's an urgent need for optimized point cloud denoising, current point outlier removal approaches, an essential step for denoising, rely heavily on handcrafted strategies and are not adapted for higher-level tasks, such as classification. To address this issue, we introduce an innovative point outlier cleansing method that harnesses the power of downstream classification models. Using gradient-based attribution analysis, we define a novel concept: point risk. Drawing inspiration from tail risk minimization in finance, we recast the outlier removal process as an optimization problem, named PointCVaR. Extensive experiments show that our proposed technique not only robustly filters diverse point cloud outliers but also consistently and significantly enhances existing robust methods for point cloud classification. A notable feature of our approach is its effectiveness in defending against the latest threat of backdoor attacks in point clouds.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow

Chaoyang Wang
Xiangtai Li
Lu Qi
Henghui Ding
Yunhai Tong
Ming-Hsuan Yang

Semantic segmentation and semantic image synthesis are two representative tasks in visual perception and generation. While existing methods consider them as two distinct tasks, we propose a unified framework (SemFlow) and model them as a pair of reverse problems. Specifically, motivated by rectified flow theory, we train an ordinary differential equation (ODE) model to transport between the distributions of real images and semantic masks. As the training object is symmetric, samples belonging to the two distributions, images and semantic masks, can be effortlessly transferred reversibly. For semantic segmentation, our approach solves the contradiction between the randomness of diffusion outputs and the uniqueness of segmentation results. For image synthesis, we propose a finite perturbation approach to enhance the diversity of generated results without changing the semantic categories. Experiments show that our SemFlow achieves competitive results on semantic segmentation and semantic image synthesis tasks. We hope this simple framework will motivate people to rethink the unification of low-level and high-level vision.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Transferable Adversarial Attacks on SAM and Its Downstream Models

Song Xia
Wenhan Yang
Yi Yu
Xun Lin
Henghui Ding
Lingyu Duan
Xudong Jiang

The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats of adverse usage. This paper, for the first time, explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM), by solely utilizing the information from the open-sourced SAM. In contrast to prevailing transfer-based adversarial attacks, we demonstrate the existence of adversarial dangers even without accessing the downstream task and dataset to train a similar surrogate model. To enhance the effectiveness of the adversarial attack towards models fine-tuned on unknown datasets, we propose a universal meta-initialization (UMI) algorithm to extract the intrinsic vulnerability inherent in the foundation model, which is then utilized as the prior knowledge to guide the generation of adversarial perturbations. Moreover, by formulating the gradient difference in the attacking process between the open-sourced SAM and its fine-tuned downstream models, we theoretically demonstrate that a deviation occurs in the adversarial update direction by directly maximizing the distance of encoded feature embeddings in the open-sourced SAM. Consequently, we propose a gradient robust loss that simulates the associated uncertainty with gradient-based noise augmentation to enhance the robustness of generated adversarial examples (AEs) towards this deviation, thus improving the transferability. Extensive experiments demonstrate the effectiveness of the proposed universal meta-initialized and gradient robust adversarial attack (UMI-GRAT) toward SAMs and their downstream models. Code is available at https: //github. com/xiasong0501/GRAT.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Decoupling with Entropy-based Equalization for Semi-Supervised Semantic Segmentation

Chuanghao Ding
Jianrong Zhang
Henghui Ding
Hongwei Zhao
Zhihui Wang
Tengfei Xing
Runbo Hu

Semi-supervised semantic segmentation methods are the main solution to alleviate the problem of high annotation consumption in semantic segmentation. However, the class imbalance problem makes the model favor the head classes with sufficient training samples, resulting in poor performance of the tail classes. To address this issue, we propose a Decoupled Semi-Supervise Semantic Segmentation (DeS4) framework based on the teacher-student model. Specifically, we first propose a decoupling training strategy to split the training of the encoder and segmentation decoder, aiming at a balanced decoder. Then, a non-learnable prototype-based segmentation head is proposed to regularize the category representation distribution consistency and perform a better connection between the teacher model and the student model. Furthermore, a Multi-Entropy Sampling (MES) strategy is proposed to collect pixel representation for updating the shared prototype to get a class-unbiased head. We conduct extensive experiments of the proposed DeS4 on two challenging benchmarks (PASCAL VOC 2012 and Cityscapes) and achieve remarkable improvements over the previous state-of-the-art methods.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

Mengyu Wang
Henghui Ding
Jun Hao Liew
Jiajun Liu
Yao Zhao
Yunchao Wei

In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by interpreting segmentation refinement as a data generation process. As a result, the refinement process can be smoothly implemented through a series of denoising diffusion steps. Specifically, SegRefiner takes coarse masks as inputs and refines them using a discrete diffusion process. By predicting the label and corresponding states-transition probabilities for each pixel, SegRefiner progressively refines the noisy masks in a conditional denoising manner. To assess the effectiveness of SegRefiner, we conduct comprehensive experiments on various segmentation tasks, including semantic segmentation, instance segmentation, and dichotomous image segmentation. The results demonstrate the superiority of our SegRefiner from multiple aspects. Firstly, it consistently improves both the segmentation metrics and boundary metrics across different types of coarse masks. Secondly, it outperforms previous model-agnostic refinement methods by a significant margin. Lastly, it exhibits a strong capability to capture extremely fine details when refining high-resolution images. The source code and trained models are available at SegRefiner. git

PDF Details

NeurIPS Conference 2022 Conference Paper

Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging

Yuanhao Cai
Jing Lin
Haoqian Wang
Xin Yuan
Henghui Ding
Yulun Zhang
Radu Timofte
Luc V Gool

In coded aperture snapshot spectral compressive imaging (CASSI) systems, hyperspectral image (HSI) reconstruction methods are employed to recover the spatial-spectral signal from a compressed measurement. Among these algorithms, deep unfolding methods demonstrate promising performance but suffer from two issues. Firstly, they do not estimate the degradation patterns and ill-posedness degree from CASSI to guide the iterative learning. Secondly, they are mainly CNN-based, showing limitations in capturing long-range dependencies. In this paper, we propose a principled Degradation-Aware Unfolding Framework (DAUF) that estimates parameters from the compressed image and physical mask, and then uses these parameters to control each iteration. Moreover, we customize a novel Half-Shuffle Transformer (HST) that simultaneously captures local contents and non-local dependencies. By plugging HST into DAUF, we establish the first Transformer-based deep unfolding method, Degradation-Aware Unfolding Half-Shuffle Transformer (DAUHST), for HSI reconstruction. Experiments show that DAUHST surpasses state-of-the-art methods while requiring cheaper computational and memory costs. Code and models are publicly available at https: //github. com/caiyuanhao1998/MST

PDF Details

NeurIPS Conference 2022 Conference Paper

Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning

Weicong Liang
Yuhui Yuan
Henghui Ding
Xiao Luo
Weihong Lin
Ding Jia
Zheng Zhang
Chao Zhang

Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens. Many advanced approaches have been developed to reduce the total number of tokens in the large-scale vision transformers, especially for image classification tasks. Typically, they select a small group of essential tokens according to their relevance with the [\texttt{class}] token, then fine-tune the weights of the vision transformer. Such fine-tuning is less practical for dense prediction due to the much heavier computation and GPU memory cost than image classification. In this paper, we focus on a more challenging problem, \ie, accelerating large-scale vision transformers for dense prediction without any additional re-training or fine-tuning. In response to the fact that high-resolution representations are necessary for dense prediction, we present two non-parametric operators, a \emph{token clustering layer} to decrease the number of tokens and a \emph{token reconstruction layer} to increase the number of tokens. The following steps are performed to achieve this: (i) we use the token clustering layer to cluster the neighboring tokens together, resulting in low-resolution representations that maintain the spatial structures; (ii) we apply the following transformer layers only to these low-resolution representations or clustered tokens; and (iii) we use the token reconstruction layer to re-create the high-resolution representations from the refined low-resolution representations. The results obtained by our method are promising on five dense prediction tasks including object detection, semantic segmentation, panoptic segmentation, instance segmentation, and depth estimation. Accordingly, our method accelerates $40\%\uparrow$ FPS and saves $30\%\downarrow$ GFLOPs of ``Segmenter+ViT-L/$16$'' while maintaining $99. 5\%$ of the performance on ADE$20$K without fine-tuning the official weights.

PDF Details

ICML Conference 2022 Conference Paper

Flow-Guided Sparse Transformer for Video Deblurring

Jing Lin
Yuanhao Cai
Xiaowan Hu
Haoqian Wang
Youliang Yan
Xueyi Zou
Henghui Ding
Yulun Zhang 0001

Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring. However, CNN-based methods show limitations in capturing long-range dependencies and modeling non-local self-similarity. In this paper, we propose a novel framework, Flow-Guided Sparse Transformer (FGST), for video deblurring. In FGST, we customize a self-attention module, Flow-Guided Sparse Window-based Multi-head Self-Attention (FGSW-MSA). For each $query$ element on the blurry reference frame, FGSW-MSA enjoys the guidance of the estimated optical flow to globally sample spatially sparse yet highly related $key$ elements corresponding to the same scene patch in neighboring frames. Besides, we present a Recurrent Embedding (RE) mechanism to transfer information from past frames and strengthen long-range temporal dependencies. Comprehensive experiments demonstrate that our proposed FGST outperforms state-of-the-art (SOTA) methods on both DVD and GOPRO datasets and yields visually pleasant results in real video deblurring. https: //github. com/linjing7/VR-Baseline

Details

NeurIPS Conference 2021 Conference Paper

Adaptive Data Augmentation on Temporal Graphs

Yiwei Wang
Yujun Cai
Yuxuan Liang
Henghui Ding
Changhu Wang
Siddharth Bhatia
Bryan Hooi

Temporal Graph Networks (TGNs) are powerful on modeling temporal graph data based on their increased complexity. Higher complexity carries with it a higher risk of overfitting, which makes TGNs capture random noise instead of essential semantic information. To address this issue, our idea is to transform the temporal graphs using data augmentation (DA) with adaptive magnitudes, so as to effectively augment the input features and preserve the essential semantic information. Based on this idea, we present the MeTA (Memory Tower Augmentation) module: a multi-level module that processes the augmented graphs of different magnitudes on separate levels, and performs message passing across levels to provide adaptively augmented inputs for every prediction. MeTA can be flexibly applied to the training of popular TGNs to improve their effectiveness without increasing their time complexity. To complement MeTA, we propose three DA strategies to realistically model noise by modifying both the temporal and topological features. Empirical results on standard datasets show that MeTA yields significant gains for the popular TGN models on edge prediction and node classification in an efficient manner.

PDF Details

NeurIPS Conference 2021 Conference Paper

Directed Graph Contrastive Learning

Zekun Tong
Yuxuan Liang
Henghui Ding
Yongxing Dai
Xinke Li
Changhu Wang

Graph Contrastive Learning (GCL) has emerged to learn generalizable representations from contrastive views. However, it is still in its infancy with two concerns: 1) changing the graph structure through data augmentation to generate contrastive views may mislead the message passing scheme, as such graph changing action deprives the intrinsic graph structural information, especially the directional structure in directed graphs; 2) since GCL usually uses predefined contrastive views with hand-picking parameters, it does not take full advantage of the contrastive information provided by data augmentation, resulting in incomplete structure information for models learning. In this paper, we design a directed graph data augmentation method called Laplacian perturbation and theoretically analyze how it provides contrastive information without changing the directed graph structure. Moreover, we present a directed graph contrastive learning framework, which dynamically learns from all possible contrastive views generated by Laplacian perturbation. Then we train it using multi-task curriculum learning to progressively learn from multiple easy-to-difficult contrastive views. We empirically show that our model can retain more structural features of directed graphs than other GCL models because of its ability to provide complete contrastive information. Experiments on various benchmarks reveal our dominance over the state-of-the-art approaches.

PDF Details