Search Results for author: Hongkai Xiong

Found 62 papers, 20 papers with code

Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation

no code implementations ICCV 2023 Shuangrui Ding, Peisen Zhao, Xiaopeng Zhang, Rui Qian, Hongkai Xiong, Qi Tian

Based on the STA score, we are able to progressively prune the tokens without introducing any additional parameters or requiring further re-training.

Video Recognition

ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting

no code implementations18 Jul 2023 Hongwei Zheng, Han Li, Bowen Shi, Wenrui Dai, Botao Wan, Yu Sun, Min Guo, Hongkai Xiong

Recent 2D-to-3D human pose estimation (HPE) utilizes temporal consistency across sequences to alleviate the depth ambiguity problem but ignore the action related prior knowledge hidden in the pose sequence.

3D Human Pose Estimation

Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners

no code implementations28 Jun 2023 Bowen Shi, Xiaopeng Zhang, Yaoming Wang, Jin Li, Wenrui Dai, Junni Zou, Hongkai Xiong, Qi Tian

In order to better obtain both discrimination and diversity, we propose a simple but effective Hybrid Distillation strategy, which utilizes both the supervised/CL teacher and the MIM teacher to jointly guide the student model.

Contrastive Learning Representation Learning

Learned Lossless Compression for JPEG via Frequency-Domain Prediction

no code implementations5 Mar 2023 Jixiang Luo, Shaohui Li, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

In this paper, we propose a novel framework for learned lossless compression of JPEG images that achieves end-to-end optimized prediction of the distribution of decoded DCT coefficients.

Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation

no code implementations15 Feb 2023 Han Li, Bowen Shi, Wenrui Dai, Hongwei Zheng, Botao Wang, Yu Sun, Min Guo, Chenlin Li, Junni Zou, Hongkai Xiong

There has been a recent surge of interest in introducing transformers to 3D human pose estimation (HPE) due to their powerful capabilities in modeling long-term dependencies.

3D Human Pose Estimation

Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition

1 code implementation CVPR 2023 Yaoming Wang, Bowen Shi, Xiaopeng Zhang, Jin Li, Yuchen Liu, Wenrui Dai, Chenglin Li, Hongkai Xiong, Qi Tian

To mitigate the computational and storage demands, recent research has explored Parameter-Efficient Fine-Tuning (PEFT), which focuses on tuning a minimal number of parameters for efficient adaptation.

Towards Unsupervised Domain Generalization for Face Anti-Spoofing

no code implementations ICCV 2023 Yuchen Liu, Yabo Chen, Mengran Gou, Chun-Ting Huang, Yaoming Wang, Wenrui Dai, Hongkai Xiong

In this paper, we propose the first Unsupervised Domain Generalization framework for Face Anti-Spoofing, namely UDG-FAS, which could exploit large amounts of easily accessible unlabeled data to learn generalizable features for enhancing the low-data regime of FAS.

Domain Generalization Face Anti-Spoofing

Dual adaptive training of photonic neural networks

1 code implementation9 Dec 2022 Ziyang Zheng, Zhengyang Duan, Hang Chen, Rui Yang, Sheng Gao, Haiou Zhang, Hongkai Xiong, Xing Lin

Photonic neural network (PNN) is a remarkable analog artificial intelligence (AI) accelerator that computes with photons instead of electrons to feature low latency, high energy efficiency, and high parallelism.

Image Classification

CPPF++: Uncertainty-Aware Sim2Real Object Pose Estimation by Vote Aggregation

1 code implementation24 Nov 2022 Yang You, Wenhao He, Jin Liu, Hongkai Xiong, Weiming Wang, Cewu Lu

To address the challenge of voting collision, we model voting uncertainty by estimating the probabilistic distribution of each point pair within the canonical space.

Pose Estimation

Lightweight network towards real-time image denoising on mobile devices

no code implementations9 Nov 2022 Zhuoqun Liu, Meiguang Jin, Ying Chen, Huaida Liu, Canqian Yang, Hongkai Xiong

In this paper, we identify the real bottlenecks that affect the CNN-based models' run-time performance on mobile devices: memory access cost and NPU-incompatible operations, and build the model based on these.

Image Denoising

SdAE: Self-distillated Masked Autoencoder

1 code implementation31 Jul 2022 Yabo Chen, Yuchen Liu, Dongsheng Jiang, Xiaopeng Zhang, Wenrui Dai, Hongkai Xiong, Qi Tian

We also analyze how to build good views for the teacher branch to produce latent representation from the perspective of information bottleneck.

Descriptive Self-Supervised Learning

Dual Contrastive Learning for Spatio-temporal Representation

no code implementations12 Jul 2022 Shuangrui Ding, Rui Qian, Hongkai Xiong

In this way, the static scene and the dynamic motion are simultaneously encoded into the compact RGB representation.

Contrastive Learning Representation Learning

Masked Autoencoders are Robust Data Augmentors

1 code implementation10 Jun 2022 Haohang Xu, Shuangrui Ding, Xiaopeng Zhang, Hongkai Xiong, Qi Tian

Specifically, MRA consistently enhances the performance on supervised, semi-supervised as well as few-shot classification.

Image Augmentation Image Classification +1

Optimization-based Block Coordinate Gradient Coding for Mitigating Partial Stragglers in Distributed Learning

no code implementations6 Jun 2022 Qi Wang, Ying Cui, Chenglin Li, Junni Zou, Hongkai Xiong

To reduce computational complexity, we first transform each to an equivalent but much simpler discrete problem with N\llL variables representing the partition of the L coordinates into N blocks, each with identical redundancy.

Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpooling

no code implementations31 May 2022 Mingxing Xu, Chenglin Li, Wenrui Dai, Siheng Chen, Junni Zou, Pascal Frossard, Hongkai Xiong

Specifically, adaptive spherical wavelets are learned with a lifting structure that consists of trainable lifting operators (i. e., update and predict operators).

LiftPool: Lifting-based Graph Pooling for Hierarchical Graph Representation Learning

no code implementations27 Apr 2022 Mingxing Xu, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

Subsequently, this local information is aligned and propagated to the preserved nodes to alleviate information loss in graph coarsening.

Graph Classification Graph Representation Learning

Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networks

1 code implementation25 Apr 2022 Ziyang Zheng, Wenrui Dai, Duoduo Xue, Chenglin Li, Junni Zou, Hongkai Xiong

This framework is general to endow arbitrary DNNs for solving linear inverse problems with convergence guarantees.

Compressive Sensing

All-optical graph representation learning using integrated diffractive photonic computing units

no code implementations23 Apr 2022 Tao Yan, Rui Yang, Ziyang Zheng, Xing Lin, Hongkai Xiong, Qionghai Dai

Photonic neural networks perform brain-inspired computations using photons instead of electrons that can achieve substantially improved computing performance.

Graph Representation Learning

Contrastive Regression for Domain Adaptation on Gaze Estimation

no code implementations CVPR 2022 Yaoming Wang, Yangzhou Jiang, Jin Li, Bingbing Ni, Wenrui Dai, Chenglin Li, Hongkai Xiong, Teng Li

Appearance-based Gaze Estimation leverages deep neural networks to regress the gaze direction from monocular images and achieve impressive performance.

Domain Generalization Gaze Estimation +1

Hierarchical Graph Networks for 3D Human Pose Estimation

1 code implementation23 Nov 2021 Han Li, Bowen Shi, Wenrui Dai, Yabo Chen, Botao Wang, Yu Sun, Min Guo, Chenlin Li, Junni Zou, Hongkai Xiong

Recent 2D-to-3D human pose estimation works tend to utilize the graph structure formed by the topology of the human skeleton.

3D Human Pose Estimation

Motion-aware Contrastive Video Representation Learning via Foreground-background Merging

1 code implementation CVPR 2022 Shuangrui Ding, Maomao Li, Tianyu Yang, Rui Qian, Haohang Xu, Qingyi Chen, Jue Wang, Hongkai Xiong

To alleviate such bias, we propose \textbf{F}oreground-b\textbf{a}ckground \textbf{Me}rging (FAME) to deliberately compose the moving foreground region of the selected video onto the static background of others.

Action Recognition Contrastive Learning +1

Variance Reduced Domain Randomization for Policy Gradient

no code implementations29 Sep 2021 Yuankun Jiang, Chenglin Li, Wenrui Dai, Junni Zou, Hongkai Xiong

In this paper, we theoretically derive a bias-free and state/environment-dependent optimal baseline for DR, and analytically show its ability to achieve further variance reduction over the standard constant and state-dependent baselines for DR. We further propose a variance reduced domain randomization (VRDR) approach for policy gradient methods, to strike a tradeoff between the variance reduction and computational complexity in practice.

Policy Gradient Methods

Understanding Self-supervised Learning via Information Bottleneck Principle

no code implementations29 Sep 2021 Jin Li, Yaoming Wang, Dongsheng Jiang, Xiaopeng Zhang, Wenrui Dai, Hongkai Xiong

To address this issue, we introduce the information bottleneck principle and propose the Self-supervised Variational Information Bottleneck (SVIB) learning framework.

Contrastive Learning Self-Supervised Learning

Graph Convolutional Networks via Adaptive Filter Banks

no code implementations29 Sep 2021 Xing Gao, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong, Pascal Frossard

Graph convolutional networks have been a powerful tool in representation learning of networked data.

Representation Learning

Graph Neural Networks With Lifting-based Adaptive Graph Wavelets

no code implementations3 Aug 2021 Mingxing Xu, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong, Pascal Frossard

To ensure that the learned graph representations are invariant to node permutations, a layer is employed at the input of the networks to reorder the nodes according to their local topology information.

Graph Representation Learning

Bag of Instances Aggregation Boosts Self-supervised Distillation

1 code implementation ICLR 2022 Haohang Xu, Jiemin Fang, Xiaopeng Zhang, Lingxi Xie, Xinggang Wang, Wenrui Dai, Hongkai Xiong, Qi Tian

Here bag of instances indicates a set of similar samples constructed by the teacher and are grouped within a bag, and the goal of distillation is to aggregate compact representations over the student with respect to instances in a bag.

Contrastive Learning Self-Supervised Learning

Message Passing in Graph Convolution Networks via Adaptive Filter Banks

no code implementations18 Jun 2021 Xing Gao, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong, Pascal Frossard

Furthermore, each filter in the spectral domain corresponds to a message passing scheme, and diverse schemes are implemented via the filter bank.

Graph Classification Representation Learning

Multi-dataset Pretraining: A Unified Model for Semantic Segmentation

no code implementations8 Jun 2021 Bowen Shi, Xiaopeng Zhang, Haohang Xu, Wenrui Dai, Junni Zou, Hongkai Xiong, Qi Tian

This is achieved by first pretraining the network via the proposed pixel-to-prototype contrastive loss over multiple datasets regardless of their taxonomy labels, and followed by fine-tuning the pretrained model over specific dataset as usual.

Semantic Segmentation

Light Field Reconstruction via Deep Adaptive Fusion of Hybrid Lenses

1 code implementation14 Feb 2021 Jing Jin, Mantang Guo, Junhui Hou, Hui Liu, Hongkai Xiong

Besides, to promote the effectiveness of our method trained with simulated hybrid data on real hybrid data captured by a hybrid LF imaging system, we carefully design the network architecture and the training strategy.

VEM-GCN: Topology Optimization with Variational EM for Graph Convolutional Networks

no code implementations1 Jan 2021 Rui Yang, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

In the variational E-step, graph topology is optimized by approximating the posterior probability distribution of the latent adjacency matrix with a neural network learned from node embeddings.

Classification General Classification +2

Learning Latent Architectural Distribution in Differentiable Neural Architecture Search via Variational Information Maximization

no code implementations ICCV 2021 Yaoming Wang, Yuchen Liu, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

Existing differentiable neural architecture search approaches simply assume the architectural distribution on each edge is independent of each other, which conflicts with the intrinsic properties of architecture.

Neural Architecture Search

Monotonic Robust Policy Optimization with Model Discrepancy

no code implementations1 Jan 2021 Yuankun Jiang, Chenglin Li, Junni Zou, Wenrui Dai, Hongkai Xiong

To mitigate the model discrepancy between training and target (testing) environments, domain randomization (DR) can generate plenty of environments with a sufficient diversity by randomly sampling environment parameters in simulator.

PAC-Bayesian Randomized Value Function with Informative Prior

no code implementations1 Jan 2021 Yuankun Jiang, Chenglin Li, Junni Zou, Wenrui Dai, Hongkai Xiong

To address this, in this paper, we propose a Bayesian linear regression with informative prior (IP-BLR) operator to leverage the data-dependent prior in the learning process of randomized value function, which can leverage the statistics of training results from previous iterations.

Reinforcement Learning (RL)

NCGNN: Node-Level Capsule Graph Neural Network for Semisupervised Classification

no code implementations7 Dec 2020 Rui Yang, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

Therefore, it can relieve the over-smoothing issue and learn effective node representations over graphs with homophily or heterophily.

Classification Node Classification

Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning

no code implementations4 Dec 2020 Haohang Xu, Xiaopeng Zhang, Hao Li, Lingxi Xie, Hongkai Xiong, Qi Tian

In this paper, we propose a hierarchical semantic alignment strategy via expanding the views generated by a single image to \textbf{Cross-samples and Multi-level} representation, and models the invariance to semantically similar images in a hierarchical way.

Contrastive Learning Representation Learning +2

Batch Normalization with Enhanced Linear Transformation

1 code implementation28 Nov 2020 Yuhui Xu, Lingxi Xie, Cihang Xie, Jieru Mei, Siyuan Qiao, Wei Shen, Hongkai Xiong, Alan Yuille

Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data distributions.

Center-wise Local Image Mixture For Contrastive Representation Learning

no code implementations5 Nov 2020 Hao Li, Xiaopeng Zhang, Hongkai Xiong

Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples.

Contrastive Learning Data Augmentation +3

MimicNorm: Weight Mean and Last BN Layer Mimic the Dynamic of Batch Normalization

1 code implementation19 Oct 2020 Wen Fei, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

We leverage the neural tangent kernel (NTK) theory to prove that our weight mean operation whitens activations and transits network into the chaotic regime like BN layer, and consequently, leads to an enhanced convergence.

K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations

no code implementations27 Jul 2020 Haohang Xu, Hongkai Xiong, Guo-Jun Qi

In this paper, we propose the $K$-Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual instances.

Contrastive Learning

Distilling Object Detectors with Task Adaptive Regularization

no code implementations23 Jun 2020 Ruoyu Sun, Fuhui Tang, Xiaopeng Zhang, Hongkai Xiong, Qi Tian

Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a larger teacher model, is one of the promising solutions for model miniaturization.

Knowledge Distillation Region Proposal

Graph Pooling with Node Proximity for Hierarchical Representation Learning

no code implementations19 Jun 2020 Xing Gao, Wenrui Dai, Chenglin Li, Hongkai Xiong, Pascal Frossard

In this paper, we propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology.

Graph Classification Representation Learning

Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events

no code implementations9 May 2020 Weiyao Lin, Huabin Liu, Shizhan Liu, Yuxi Li, Rui Qian, Tao Wang, Ning Xu, Hongkai Xiong, Guo-Jun Qi, Nicu Sebe

To this end, we present a new large-scale dataset with comprehensive annotations, named Human-in-Events or HiEve (Human-centric video analysis in complex Events), for the understanding of human motions, poses, and actions in a variety of realistic events, especially in crowd & complex events.

Action Recognition Pose Estimation

TRP: Trained Rank Pruning for Efficient Deep Neural Networks

1 code implementation30 Apr 2020 Yuhui Xu, Yuxi Li, Shuai Zhang, Wei Wen, Botao Wang, Yingyong Qi, Yiran Chen, Weiyao Lin, Hongkai Xiong

The TRP trained network inherently has a low-rank structure, and is approximated with negligible performance loss, thus eliminating the fine-tuning process after low rank decomposition.

Latency-Aware Differentiable Neural Architecture Search

1 code implementation17 Jan 2020 Yuhui Xu, Lingxi Xie, Xiaopeng Zhang, Xin Chen, Bowen Shi, Qi Tian, Hongkai Xiong

However, these methods suffer the difficulty in optimizing network, so that the searched network is often unfriendly to hardware.

Neural Architecture Search

Spatial-Temporal Transformer Networks for Traffic Flow Forecasting

1 code implementation9 Jan 2020 Mingxing Xu, Wenrui Dai, Chunmiao Liu, Xing Gao, Weiyao Lin, Guo-Jun Qi, Hongkai Xiong

In this paper, we propose a novel paradigm of Spatial-Temporal Transformer Networks (STTNs) that leverages dynamical directed spatial dependencies and long-range temporal dependencies to improve the accuracy of long-term traffic forecasting.

Traffic Prediction

FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers

no code implementations29 Dec 2019 Haohang Xu, Hongkai Xiong, Guo-Jun Qi

To this end, we present a novel regularization mechanism by learning the change of feature representations induced by a distribution of transformations without using the labels of data examples.

Data Augmentation Few-Shot Learning +1

AETv2: AutoEncoding Transformations for Self-Supervised Representation Learning by Minimizing Geodesic Distances in Lie Groups

no code implementations16 Nov 2019 Feng Lin, Haohang Xu, Houqiang Li, Hongkai Xiong, Guo-Jun Qi

For this reason, we should use the geodesic to characterize how an image transform along the manifold of a transformation group, and adopt its length to measure the deviation between transformations.

Representation Learning Self-Supervised Learning

Trained Rank Pruning for Efficient Deep Neural Networks

1 code implementation9 Oct 2019 Yuhui Xu, Yuxi Li, Shuai Zhang, Wei Wen, Botao Wang, Wenrui Dai, Yingyong Qi, Yiran Chen, Weiyao Lin, Hongkai Xiong

To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations.

PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search

7 code implementations ICLR 2020 Yuhui Xu, Lingxi Xie, Xiaopeng Zhang, Xin Chen, Guo-Jun Qi, Qi Tian, Hongkai Xiong

Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching for an optimal architecture.

Neural Architecture Search

iPool -- Information-based Pooling in Hierarchical Graph Neural Networks

no code implementations1 Jul 2019 Xing Gao, Hongkai Xiong, Pascal Frossard

In this paper, we propose a parameter-free pooling operator, called iPool, that permits to retain the most informative features in arbitrary graphs.

Graph Classification

Group Re-Identification with Multi-grained Matching and Integration

no code implementations17 May 2019 Weiyao Lin, Yuxi Li, Hao Xiao, John See, Junni Zou, Hongkai Xiong, Jingdong Wang, Tao Mei

The task of re-identifying groups of people underdifferent camera views is an important yet less-studied problem. Group re-identification (Re-ID) is a very challenging task sinceit is not only adversely affected by common issues in traditionalsingle object Re-ID problems such as viewpoint and human posevariations, but it also suffers from changes in group layout andgroup membership.

Trained Rank Pruning for Efficient Deep Neural Networks

1 code implementation6 Dec 2018 Yuhui Xu, Yuxi Li, Shuai Zhang, Wei Wen, Botao Wang, Yingyong Qi, Yiran Chen, Weiyao Lin, Hongkai Xiong

We propose Trained Rank Pruning (TRP), which iterates low rank approximation and training.


DNQ: Dynamic Network Quantization

no code implementations6 Dec 2018 Yuhui Xu, Shuai Zhang, Yingyong Qi, Jiaxian Guo, Weiyao Lin, Hongkai Xiong

Network quantization is an effective method for the deployment of neural networks on memory and energy constrained mobile devices.


Zigzag Learning for Weakly Supervised Object Detection

no code implementations CVPR 2018 Xiaopeng Zhang, Jiashi Feng, Hongkai Xiong, Qi Tian

Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds.

object-detection Weakly Supervised Object Detection

Deep Neural Network Compression with Single and Multiple Level Quantization

1 code implementation6 Mar 2018 Yuhui Xu, Yongzhuang Wang, Aojun Zhou, Weiyao Lin, Hongkai Xiong

In this paper, we propose two novel network quantization approaches, single-level network quantization (SLQ) for high-bit quantization and multi-level network quantization (MLQ) for extremely low-bit quantization (ternary). We are the first to consider the network quantization from both width and depth level.

Neural Network Compression Quantization

Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion

no code implementations20 Nov 2017 Weiyao Lin, Yang Mi, Jianxin Wu, Ke Lu, Hongkai Xiong

In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for representing actions, and 2) reducing the asynchrony between different information streams.

Action Recognition Temporal Action Localization

Picking Deep Filter Responses for Fine-Grained Image Recognition

no code implementations CVPR 2016 Xiaopeng Zhang, Hongkai Xiong, Wengang Zhou, Weiyao Lin, Qi Tian

Recognizing fine-grained sub-categories such as birds and dogs is extremely challenging due to the highly localized and subtle differences in some specific parts.

Fine-Grained Image Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.