Search Results for author: DaCheng Tao

Found 396 papers, 127 papers with code

On Dropping Clusters to Regularize Graph Convolutional Neural Networks

no code implementations ECCV 2020 Xikun Zhang, Chang Xu, DaCheng Tao

Dropout has been widely adopted to regularize graph convolutional networks (GCNs) by randomly zeroing entries of the node feature vectors and obtains promising performance on various tasks.

Action Recognition Skeleton Based Action Recognition

Label-Noise Robust Domain Adaptation

no code implementations ICML 2020 Xiyu Yu, Tongliang Liu, Mingming Gong, Kun Zhang, Kayhan Batmanghelich, DaCheng Tao

Domain adaptation aims to correct the classifiers when faced with distribution shift between source (training) and target (test) domains.

Denoising Domain Adaptation

Polysemy Deciphering Network for Human-Object Interaction Detection

1 code implementation ECCV 2020 Xubin Zhong, Changxing Ding, Xian Qu, DaCheng Tao

First, PD-Net augments human pose and spatial features for HOI detection using language priors, enabling the verb classifiers to receive language hints that reduce the intra-class variation of the same verb.

Human-Object Interaction Detection Scene Understanding

Hallucinating Visual Instances in Total Absentia

no code implementations ECCV 2020 Jiayan Qiu, Yiding Yang, Xinchao Wang, DaCheng Tao

This seemingly minor difference in fact makes the HVITA a much challenging task, as the restoration algorithm would have to not only infer the category of the object in total absentia, but also hallucinate an object of which the appearance is consistent with the background.

Graph Convolutional Network Image Inpainting

LTF: A Label Transformation Framework for Correcting Label Shift

no code implementations ICML 2020 Jiaxian Guo, Mingming Gong, Tongliang Liu, Kun Zhang, DaCheng Tao

Distribution shift is a major obstacle to the deployment of current deep learning models on real-world problems.

Deep Streaming Label Learning

no code implementations ICML 2020 Zhen Wang, Liu Liu, DaCheng Tao

In order to fill in these research gaps, we propose a novel deep neural network (DNN) based framework, Deep Streaming Label Learning (DSLL), to classify instances with newly emerged labels effectively.

Multi-Label Learning

TransVOD: End-to-end Video Object Detection with Spatial-Temporal Transformers

no code implementations13 Jan 2022 Qianyu Zhou, Xiangtai Li, Lu He, Yibo Yang, Guangliang Cheng, Yunhai Tong, Lizhuang Ma, DaCheng Tao

Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.

Optical Flow Estimation Video Object Detection

Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis

no code implementations13 Jan 2022 Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, Hua Jin, DaCheng Tao

To this end, we propose a knowledge graph augmented network (KGAN), which aims to effectively incorporate external knowledge with explicitly syntactic and contextual information.

Aspect-Based Sentiment Analysis Knowledge Graphs +1

SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection

1 code implementation6 Jan 2022 Chen Chen, Zhe Chen, Jing Zhang, DaCheng Tao

We observe that the prevailing set abstraction design for down-sampling points may maintain too much unimportant background information that can affect feature learning for detecting objects.

3D Object Detection

Quality-aware Part Models for Occluded Person Re-identification

no code implementations1 Jan 2022 Pengfei Wang, Changxing Ding, Zhiyin Shao, Zhibin Hong, Shengli Zhang, DaCheng Tao

Existing approaches typically rely on outside tools to infer visible body parts, which may be suboptimal in terms of both computational efficiency and ReID accuracy.

Person Re-Identification

Few-shot Backdoor Defense Using Shapley Estimation

no code implementations30 Dec 2021 Jiyang Guan, Zhuozhuo Tu, Ran He, DaCheng Tao

Deep neural networks have achieved impressive performance in a variety of tasks over the last decade, such as autonomous driving, face recognition, and medical diagnosis.

Autonomous Driving Face Recognition +1

PONet: Robust 3D Human Pose Estimation via Learning Orientations Only

no code implementations21 Dec 2021 Jue Wang, Shaoli Huang, Xinchao Wang, DaCheng Tao

Conventional 3D human pose estimation relies on first detecting 2D body keypoints and then solving the 2D to 3D correspondence problem. Despite the promising results, this learning paradigm is highly dependent on the quality of the 2D keypoint detector, which is inevitably fragile to occlusions and out-of-image absences. In this paper, we propose a novel Pose Orientation Net (PONet) that is able to robustly estimate 3D pose by learning orientations only, hence bypassing the error-prone keypoint detector in the absence of image evidence.

3D Human Pose Estimation

Self-Ensembling GAN for Cross-Domain Semantic Segmentation

no code implementations15 Dec 2021 Yonghao Xu, Fengxiang He, Bo Du, Liangpei Zhang, DaCheng Tao

In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN.

Semantic Segmentation

DGL-GAN: Discriminator Guided Learning for GAN Compression

no code implementations13 Dec 2021 Yuesong Tian, Li Shen, DaCheng Tao, Zhifeng Li, Wei Liu

Generative Adversarial Networks (GANs) with high computation costs, e. g., BigGAN and StyleGAN2, have achieved remarkable results in synthesizing high resolution and diverse images with high fidelity from random noises.

Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer

no code implementations12 Dec 2021 Shiye Lei, Zhuozhuo Tu, Leszek Rutkowski, Feng Zhou, Li Shen, Fengxiang He, DaCheng Tao

Bayesian neural networks (BNNs) have become a principal approach to alleviate overconfident predictions in deep learning, but they often suffer from scaling issues due to a large number of distribution parameters.

Adversarial Robustness Variational Inference

Recurrent Glimpse-based Decoder for Detection with Transformer

1 code implementation9 Dec 2021 Zhe Chen, Jing Zhang, DaCheng Tao

Then, a glimpse-based decoder is introduced to provide refined detection results based on both the glimpse features and the attention modeling outputs of the previous stage.

Spectral Complexity-scaled Generalization Bound of Complex-valued Neural Networks

no code implementations7 Dec 2021 Haowen Chen, Fengxiang He, Shiye Lei, DaCheng Tao

The bound scales with the spectral complexity, the dominant factor of which is the spectral norm product of weight matrices.

PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation

1 code implementation5 Dec 2021 Haobo Yuan, Xiangtai Li, Yibo Yang, Guangliang Cheng, Jing Zhang, Yunhai Tong, Lefei Zhang, DaCheng Tao

The recently proposed Depth-aware Video Panoptic Segmentation (DVPS) aims to predict panoptic segmentation results and depth maps in a video, which is a challenging scene understanding problem.

Depth Estimation Panoptic Segmentation +1

Dual-Flow Transformation Network for Deformable Image Registration with Region Consistency Constraint

no code implementations4 Dec 2021 Xinke Ma, Yibo Yang, Yong Xia, DaCheng Tao

In this paper, we present a novel dual-flow transformation network with region consistency constraint which maximizes the similarity of ROIs within a pair of images and estimates both global and region spatial transformations simultaneously.

Image Registration

Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction

no code implementations4 Dec 2021 Yikai Wang, Wenbing Huang, Fuchun Sun, Fengxiang He, DaCheng Tao

For the application of dense image prediction, the validity of CEN is tested by four different scenarios: multimodal fusion, cycle multimodal fusion, multitask learning, and multimodal multitask learning.

Semantic Segmentation

Video Frame Interpolation without Temporal Priors

1 code implementation NeurIPS 2020 Youjian Zhang, Chaoyue Wang, DaCheng Tao

However, in complicated real-world situations, the temporal priors of videos, i. e. frames per second (FPS) and frame exposure time, may vary from different camera sensors.

Optical Flow Estimation Video Frame Interpolation

FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis

no code implementations2 Dec 2021 Yu Feng, Benteng Ma, Jing Zhang, Shanshan Zhao, Yong Xia, DaCheng Tao

However, designing a unified BA method that can be applied to various MIA systems is challenging due to the diversity of imaging modalities (e. g., X-Ray, CT, and MRI) and analysis tasks (e. g., classification, detection, and segmentation).

Image Classification Lesion Classification +2

Gauge Equivariant Transformer

no code implementations NeurIPS 2021 Lingshen He, Yiming Dong, Yisen Wang, DaCheng Tao, Zhouchen Lin

Attention mechanism has shown great performance and efficiency in a lot of deep learning models, in which relative position encoding plays a crucial role.

Class-Disentanglement and Applications in Adversarial Detection and Defense

no code implementations NeurIPS 2021 Kaiwen Yang, Tianyi Zhou, Yonggang Zhang, Xinmei Tian, DaCheng Tao

In this paper, we propose ''class-disentanglement'' that trains a variational autoencoder $G(\cdot)$ to extract this class-dependent information as $x - G(x)$ via a trade-off between reconstructing $x$ by $G(x)$ and classifying $x$ by $D(x-G(x))$, where the former competes with the latter in decomposing $x$ so the latter retains only necessary information for classification in $x-G(x)$.

Adversarial Defense

Hierarchical Prototype Networks for Continual Graph Representation Learning

no code implementations30 Nov 2021 Xikun Zhang, Dongjin Song, DaCheng Tao

Despite significant advances in graph representation learning, little attention has been paid to the more practical continual learning scenario in which new categories of nodes (e. g., new research areas in citation networks, or new types of products in co-purchasing networks) and their associated edges are continuously emerging, causing catastrophic forgetting on previous categories.

Continual Learning Graph Representation Learning

GMFlow: Learning Optical Flow via Global Matching

1 code implementation26 Nov 2021 Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, DaCheng Tao

Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of large displacements.

Optical Flow Estimation

RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?

1 code implementation24 Nov 2021 Yufei Xu, Qiming Zhang, Jing Zhang, DaCheng Tao

In this paper, we make the first attempt to demonstrate the importance of both regions in cropping from a complete perspective and propose a simple yet effective pretext task called Region Contrastive Learning (RegionCL).

Contrastive Learning

Pruning Self-attentions into Convolutional Layers in Single Path

1 code implementation23 Nov 2021 Haoyu He, Jing Liu, Zizheng Pan, Jianfei Cai, Jing Zhang, DaCheng Tao, Bohan Zhuang

Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks.

Neural Architecture Search

Off-policy Imitation Learning from Visual Inputs

no code implementations8 Nov 2021 Zhihao Cheng, Li Shen, DaCheng Tao

We propose OPIfVI (Off-Policy Imitation from Visual Inputs), which is composed of an off-policy learning manner, data augmentation, and encoder techniques, to tackle the mentioned challenges, respectively.

Data Augmentation Imitation Learning

Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis

1 code implementation26 Oct 2021 Juhua Liu, Qihuang Zhong, Liang Ding, Hua Jin, Bo Du, DaCheng Tao

In practice, we formulate the model pretrained on the sampled instances into a knowledge guidance model and a learner model, respectively.

Aspect-Based Sentiment Analysis Transfer Learning

Theoretical understanding of adversarial reinforcement learning via mean-field optimal control

no code implementations29 Sep 2021 ZiMing Wang, Fengxiang He, Tao Cui, DaCheng Tao

A new mean-field Pontryagin's maximum principle is proposed for reinforcement learning with implicit terminal constraints.

Generalization Bounds

Lagrangian Generative Adversarial Imitation Learning with Safety

no code implementations29 Sep 2021 Zhihao Cheng, Li Shen, Meng Fang, Liu Liu, DaCheng Tao

Imitation Learning (IL) merely concentrates on reproducing expert behaviors and could take dangerous actions, which is unbearable in safety-critical scenarios.

Imitation Learning

FLBoost: On-the-Fly Fine-tuning Boosts Federated Learning via Data-free Distillation

no code implementations29 Sep 2021 Lin Zhang, Li Shen, Liang Ding, DaCheng Tao, Lingyu Duan

On the contrary, we propose a new solution: on-the-fly fine-tuning the global model in server via data-free distillation to boost its performance, dubbed FLBoost to relieve the issue of direct model aggregation.

Federated Learning

Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks

no code implementations ICCV 2021 Yongcheng Jing, Yiding Yang, Xinchao Wang, Mingli Song, DaCheng Tao

In this paper, we study a novel meta aggregation scheme towards binarizing graph neural networks (GNNs).

Learning Versatile Convolution Filters for Efficient Visual Recognition

no code implementations20 Sep 2021 Kai Han, Yunhe Wang, Chang Xu, Chunjing Xu, Enhua Wu, DaCheng Tao

A series of secondary filters can be derived from a primary filter with the help of binary masks.

Improving Neural Machine Translation by Bidirectional Training

no code implementations EMNLP 2021 Liang Ding, Di wu, DaCheng Tao

We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation.

Machine Translation Translation

Harnessing Perceptual Adversarial Patches for Crowd Counting

no code implementations16 Sep 2021 Shunchang Liu, Jiakai Wang, Aishan Liu, Yingwei Li, Yijie Gao, Xianglong Liu, DaCheng Tao

Crowd counting, which is significantly important for estimating the number of people in safety-critical scenes, has been shown to be vulnerable to adversarial examples in the physical world (e. g., adversarial patches).

Crowd Counting

RobustART: Benchmarking Robustness on Architecture Design and Training Techniques

1 code implementation11 Sep 2021 Shiyu Tang, Ruihao Gong, Yan Wang, Aishan Liu, Jiakai Wang, Xinyun Chen, Fengwei Yu, Xianglong Liu, Dawn Song, Alan Yuille, Philip H. S. Torr, DaCheng Tao

Thus, we propose RobustART, the first comprehensive Robustness investigation benchmark on ImageNet regarding ARchitecture design (49 human-designed off-the-shelf architectures and 1200+ networks from neural architecture search) and Training techniques (10+ techniques, e. g., data augmentation) towards diverse noises (adversarial, natural, and system noises).

Adversarial Robustness Data Augmentation +1

AP-10K: A Benchmark for Animal Pose Estimation in the Wild

5 code implementations28 Aug 2021 Hang Yu, Yufei Xu, Jing Zhang, Wei Zhao, Ziyu Guan, DaCheng Tao

The experimental results provide sound empirical evidence on the superiority of learning from diverse animals species in terms of both accuracy and generalization ability.

Animal Pose Estimation Domain Generalization +1

Semantic-Preserving Adversarial Text Attacks

1 code implementation23 Aug 2021 Xinghao Yang, Weifeng Liu, James Bailey, Tianqing Zhu, DaCheng Tao, Wei Liu

In this paper, we propose a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) method to examine the vulnerability of deep models.

Adversarial Text Semantic Similarity +2

Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification

1 code implementation22 Aug 2021 Pengfei Wang, Changxing Ding, Wentao Tan, Mingming Gong, Kui Jia, DaCheng Tao

In particular, the performance of our unsupervised UCF method in the MSMT17$\to$Market1501 task is better than that of the fully supervised setting on Market1501.

End2End Occluded Face Recognition by Masking Corrupted Features

1 code implementation21 Aug 2021 Haibo Qiu, Dihong Gong, Zhifeng Li, Wei Liu, DaCheng Tao

With the recent advancement of deep convolutional neural networks, significant progress has been made in general face recognition.

Face Recognition

Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization

1 code implementation ICCV 2021 Yufei Xu, Jing Zhang, DaCheng Tao

However, since the view outside the boundary is not available during warping, the resulting holes around the boundary of the stabilized frame must be discarded (i. e., cropping) to maintain visual consistency, and thus does leads to a tradeoff between stability and cropping ratio.

Video Stabilization

SynFace: Face Recognition with Synthetic Data

1 code implementation ICCV 2021 Haibo Qiu, Baosheng Yu, Dihong Gong, Zhifeng Li, Wei Liu, DaCheng Tao

We then analyze the underlying causes behind the performance gap, e. g., the poor intra-class variations and the domain gap between synthetic and real face images.

Face Generation Face Recognition

Structure-Aware Feature Generation for Zero-Shot Learning

no code implementations16 Aug 2021 Lianbo Zhang, Shaoli Huang, Xinchao Wang, Wei Liu, DaCheng Tao

In this paper, we introduce a novel structure-aware feature generation scheme, termed as SA-GAN, to explicitly account for the topological structure in learning both the latent space and the generative networks.

Zero-Shot Learning

Effective and Efficient Graph Learning for Multi-view Clustering

no code implementations15 Aug 2021 Quanxue Gao, Wei Xia, Xinbo Gao, Xiangdong Zhang, Qin Li, DaCheng Tao

Despite the impressive clustering performance and efficiency in characterizing both the relationship between data and cluster structure, existing graph-based multi-view clustering methods still have the following drawbacks.

Graph Learning

Learning Visual Affordance Grounding from Demonstration Videos

no code implementations12 Aug 2021 Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, DaCheng Tao

For the object branch, we introduce a semantic enhancement module (SEM) to make the network focus on different parts of the object according to the action classes and utilize a distillation loss to align the output features of the object branch with that of the video branch and transfer the knowledge in the video branch to the object branch.

Action Recognition

One-Shot Object Affordance Detection in the Wild

1 code implementation8 Aug 2021 Wei Zhai, Hongchen Luo, Jing Zhang, Yang Cao, DaCheng Tao

To empower robots with this ability in unseen scenarios, we first study the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.

Action Recognition Affordance Detection +1

I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection

no code implementations3 Aug 2021 Jian Ye, Jing Zhang, Juhua Liu, Bo Du, DaCheng Tao

Existing methods for arbitrary-shaped text detection in natural scenes face two critical issues, i. e., 1) fracture detections at the gaps in a text instance; and 2) inaccurate detections of arbitrary-shaped text instances with diverse background context.

Scene Text Detection

Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification

1 code implementation27 Jul 2021 Zefeng Ding, Changxing Ding, Zhiyin Shao, DaCheng Tao

Third, we introduce a Compound Ranking (CR) loss that makes use of textual descriptions for other images of the same identity to provide extra supervision, thereby effectively reducing the intra-class variance in textual features.

Person Re-Identification Text based Person Retrieval +1

DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation

1 code implementation20 Jul 2021 Li Gao, Jing Zhang, Lefei Zhang, DaCheng Tao

In addition, feature-level alignment is carried out by aligning the feature maps of the source and target images from student network using a weighted maximum mean discrepancy loss.

Semantic Segmentation Synthetic-to-Real Translation +1

Deep Automatic Natural Image Matting

1 code implementation15 Jul 2021 Jizhizi Li, Jing Zhang, DaCheng Tao

To address the problem, a novel end-to-end matting network is proposed, which can predict a generalized trimap for any image of the above types as a unified semantic representation.

Image Matting Matting

On exploring practical potentials of quantum auto-encoder with advantages

no code implementations29 Jun 2021 Yuxuan Du, DaCheng Tao

To address these issues, here we prove that QAE can be used to efficiently calculate the eigenvalues and prepare the corresponding eigenvectors of a high-dimensional quantum state with the low-rank property.

One-Shot Affordance Detection

1 code implementation28 Jun 2021 Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, DaCheng Tao

To empower robots with this ability in unseen scenarios, we consider the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.

Affordance Detection

GAN-MDF: A Method for Multi-fidelity Data Fusion in Digital Twins

no code implementations24 Jun 2021 Lixue Liu, Chao Zhang, DaCheng Tao

Multi-fidelity data fusion (MDF) methods aims to use massive LF samples and small amounts of HF samples to develop an accurate and efficient model for describing the system with a reasonable computation burden.

Accelerating variational quantum algorithms with multiple quantum processors

no code implementations24 Jun 2021 Yuxuan Du, Yang Qian, DaCheng Tao

Variational quantum algorithms (VQAs) have the potential of utilizing near-term quantum machines to gain certain computational advantages over classical methods.

Distributed Optimization

TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition

1 code implementation ICCV 2021 Wenyuan Xue, Baosheng Yu, Wen Wang, DaCheng Tao, Qingyong Li

A table arranging data in rows and columns is a very effective data structure, which has been widely used in business and scientific research.

Graph Reconstruction Table Recognition

Scene Essence

no code implementations CVPR 2021 Jiayan Qiu, Yiding Yang, Xinchao Wang, DaCheng Tao

What scene elements, if any, are indispensable for recognizing a scene?

Scene Recognition

Tree-Like Decision Distillation

no code implementations CVPR 2021 Jie Song, Haofei Zhang, Xinchao Wang, Mengqi Xue, Ying Chen, Li Sun, DaCheng Tao, Mingli Song

Knowledge distillation pursues a diminutive yet well-behaved student network by harnessing the knowledge learned by a cumbersome teacher model.

Decision Making Knowledge Distillation

Turning Frequency to Resolution: Video Super-Resolution via Event Cameras

no code implementations CVPR 2021 Yongcheng Jing, Yiding Yang, Xinchao Wang, Mingli Song, DaCheng Tao

To this end, we propose an Event-based VSR framework (E-VSR), of which the key component is an asynchronous interpolation (EAI) module that reconstructs a high-frequency (HF) video stream with uniform and tiny pixel displacements between neighboring frames from an event stream.

Video Super-Resolution

Learning Progressive Point Embeddings for 3D Point Cloud Generation

no code implementations CVPR 2021 Cheng Wen, Baosheng Yu, DaCheng Tao

The proposed dual-generators framework thus is able to progressively learn effective point embeddings for accurate point cloud generation.

Autonomous Driving Object Reconstruction +2

Local AdaGrad-Type Algorithm for Stochastic Convex-Concave Minimax Problems

no code implementations18 Jun 2021 Luofeng Liao, Li Shen, Jia Duan, Mladen Kolar, DaCheng Tao

Large scale convex-concave minimax problems arise in numerous applications, including game theory, robust training, and training of generative adversarial networks.

Progressive Multi-Granularity Training for Non-Autoregressive Translation

no code implementations Findings (ACL) 2021 Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, DaCheng Tao, Zhaopeng Tu

Non-autoregressive translation (NAT) significantly accelerates the inference process via predicting the entire target sequence.

Translation

The dilemma of quantum neural networks

1 code implementation9 Jun 2021 Yang Qian, Xinbiao Wang, Yuxuan Du, Xingyao Wu, DaCheng Tao

The core of quantum machine learning is to devise quantum models with good trainability and low generalization error bound than their classical counterparts to ensure better reliability and interpretability.

Commutative Lie Group VAE for Disentanglement Learning

1 code implementation7 Jun 2021 Xinqi Zhu, Chang Xu, DaCheng Tao

Instead, we propose to encode the data variations with groups, a structure not only can equivariantly represent variations, but can also be adaptively optimized to preserve the properties of data variations.

ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias

1 code implementation NeurIPS 2021 Yufei Xu, Qiming Zhang, Jing Zhang, DaCheng Tao

Nevertheless, vision transformers treat an image as 1D sequence of visual tokens, lacking an intrinsic inductive bias (IB) in modeling local visual structures and dealing with scale variance.

Image Classification Object Detection +1

Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss

1 code implementation6 Jun 2021 Jian Cheng, Ziyang Liu, Hao Guan, Zhenzhou Wu, Haogang Zhu, Jiyang Jiang, Wei Wen, DaCheng Tao, Tao Liu

In this paper, a novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data.

Age Estimation

Patch Slimming for Efficient Vision Transformers

no code implementations5 Jun 2021 Yehui Tang, Kai Han, Yunhe Wang, Chang Xu, Jianyuan Guo, Chao Xu, DaCheng Tao

We first identify the effective patches in the last layer and then use them to guide the patch selection process of previous layers.

Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation

no code implementations ACL 2021 Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, DaCheng Tao, Zhaopeng Tu

Results demonstrate that the proposed approach can significantly and universally improve translation quality by reducing translation errors on low-frequency words.

Knowledge Distillation Translation

Hierarchical Prototype Network for Continual Graph Representation Learning

no code implementations NeurIPS 2021 Xikun Zhang, Dongjin Song, DaCheng Tao

The key challenge is to incorporate the feature and topological information of new nodes in a continuous and effective manner such that performance over existing nodes is uninterrupted.

Continual Learning Graph Representation Learning

End-to-end One-shot Human Parsing

1 code implementation4 May 2021 Haoyu He, Jing Zhang, Bohan Zhuang, Jianfei Cai, DaCheng Tao

Previous human parsing models are limited to parsing humans into pre-defined classes, which is inflexible for applications that need to handle new classes.

Human Parsing Metric Learning +1

Privacy-Preserving Portrait Matting

1 code implementation29 Apr 2021 Jizhizi Li, Sihan Ma, Jing Zhang, DaCheng Tao

We systematically evaluate both trimap-free and trimap-based matting methods on P3M-10k and find that existing matting methods show different generalization capabilities when following the Privacy-Preserving Training (PPT) setting, i. e., training on face-blurred images and testing on arbitrary images.

Image Matting Matting

Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding

no code implementations13 Apr 2021 Di wu, Yiren Chen, Liang Ding, DaCheng Tao

Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones.

Denoising Domain Adaptation +4

Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection

1 code implementation CVPR 2021 Xubin Zhong, Xian Qu, Changxing Ding, DaCheng Tao

In this paper, we propose a novel one-stage method, namely Glance and Gaze Network (GGNet), which adaptively models a set of actionaware points (ActPoints) via glance and gaze steps.

Human-Object Interaction Detection

MRI-based Alzheimer's disease prediction via distilling the knowledge in multi-modal data

no code implementations8 Apr 2021 Hao Guan, Chaoyue Wang, DaCheng Tao

In this work, we propose a multi-modal multi-instance distillation scheme, which aims to distill the knowledge learned from multi-modal data to an MRI-based network for MCI conversion prediction.

Disease Prediction

Where and What? Examining Interpretable Disentangled Representations

1 code implementation CVPR 2021 Xinqi Zhu, Chang Xu, DaCheng Tao

We thus impose a perturbation on a certain dimension of the latent code, and expect to identify the perturbation along this dimension from the generated images so that the encoding of simple variations can be enforced.

Model Selection

Affordance Transfer Learning for Human-Object Interaction Detection

2 code implementations CVPR 2021 Zhi Hou, Baosheng Yu, Yu Qiao, Xiaojiang Peng, DaCheng Tao

The proposed method can thus be used to 1) improve the performance of HOI detection, especially for the HOIs with unseen objects; and 2) infer the affordances of novel objects.

Affordance Detection Human-Object Interaction Detection +2

Online Multiple Object Tracking with Cross-Task Synergy

1 code implementation CVPR 2021 Song Guo, Jingya Wang, Xinchao Wang, DaCheng Tao

On the other hand, such reliable embeddings can boost identity-awareness through memory aggregation, hence strengthen attention modules and suppress drifts.

Multiple Object Tracking

Towards understanding the power of quantum kernels in the NISQ era

no code implementations31 Mar 2021 Xinbiao Wang, Yuxuan Du, Yong Luo, DaCheng Tao

In this study, we fill this knowledge gap by exploiting the power of quantum kernels when the quantum system noise and sample error are considered.

Detecting Human-Object Interaction via Fabricated Compositional Learning

1 code implementation CVPR 2021 Zhi Hou, Baosheng Yu, Yu Qiao, Xiaojiang Peng, DaCheng Tao

With the proposed object fabricator, we are able to generate large-scale HOI samples for rare and unseen categories to alleviate the open long-tailed issues in HOI detection.

Human-Object Interaction Detection Scene Understanding

Manifold Regularized Dynamic Network Pruning

2 code implementations CVPR 2021 Yehui Tang, Yunhe Wang, Yixing Xu, Yiping Deng, Chao Xu, DaCheng Tao, Chang Xu

Then, the manifold relationship between instances and the pruned sub-networks will be aligned in the training procedure.

Network Pruning

Learning Compositional Representation for Few-shot Visual Question Answering

no code implementations21 Feb 2021 Dalu Guo, DaCheng Tao

Experimental results on the VQA v2. 0 validation dataset demonstrate the effectiveness of our proposed attribute network and the constraint between answers and their corresponding attributes, as well as the ability of our method to handle the answers with few training examples.

Question Answering Visual Question Answering

CPP-Net: Context-aware Polygon Proposal Network for Nucleus Segmentation

no code implementations13 Feb 2021 Shengcong Chen, Changxing Ding, Minfeng Liu, DaCheng Tao

Here, the SAP loss is based on an additional network that is pre-trained by means of mapping the centroid probability map and the pixel-to-boundary distance maps to a different nucleus representation.

AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence

no code implementations25 Jan 2021 Yunhe Wang, Mingqiang Huang, Kai Han, Hanting Chen, Wei zhang, Chunjing Xu, DaCheng Tao

With a comprehensive comparison on the performance, power consumption, hardware resource consumption and network generalization capability, we conclude the AdderNet is able to surpass all the other competitors including the classical CNN, novel memristor-network, XNOR-Net and the shift-kernel based network, indicating its great potential in future high performance and energy-efficient artificial intelligence applications.

Quantization

Collaborative Teacher-Student Learning via Multiple Knowledge Transfer

no code implementations21 Jan 2021 Liyuan Sun, Jianping Gou, Baosheng Yu, Lan Du, DaCheng Tao

However, most of the existing knowledge distillation methods consider only one type of knowledge learned from either instance features or instance relations via a specific distillation strategy in teacher-student learning.

Knowledge Distillation Model Compression +1

Bayesian Inference Forgetting

1 code implementation16 Jan 2021 Shaopeng Fu, Fengxiang He, Yue Xu, DaCheng Tao

This paper proposes a {\it Bayesian inference forgetting} (BIF) framework to realize the right to be forgotten in Bayesian inference.

Bayesian Inference Variational Inference

Neural networks behave as hash encoders: An empirical study

1 code implementation14 Jan 2021 Fengxiang He, Shiye Lei, Jianmin Ji, DaCheng Tao

We then define an {\it activation hash phase chart} to represent the space expanded by {model size}, training time, training sample size, and the encoding properties, which is divided into three canonical regions: {\it under-expressive regime}, {\it critically-expressive regime}, and {\it sufficiently-expressive regime}.

SPAGAN: Shortest Path Graph Attention Network

1 code implementation10 Jan 2021 Yiding Yang, Xinchao Wang, Mingli Song, Junsong Yuan, DaCheng Tao

SPAGAN therefore allows for a more informative and intact exploration of the graph structure and further {a} more effective aggregation of information from distant neighbors into the center node, as compared to node-based GCN methods.

Graph Attention

Stochastic Partial Swap: Enhanced Model Generalization and Interpretability for Fine-Grained Recognition

no code implementations ICCV 2021 Shaoli Huang, Xinchao Wang, DaCheng Tao

Learning mid-level representation for fine-grained recognition is easily dominated by a limited number of highly discriminative patterns, degrading its robustness and generalization capability.

Material Recognition Scene Recognition

Information-Theoretic Odometry Learning

no code implementations1 Jan 2021 Sen Zhang, Jing Zhang, DaCheng Tao

In this paper, we propose a unified information-theoretic framework for odometry learning, a crucial component of many robotics and vision tasks such as navigation and virtual reality where 6-DOF poses are required in real time.

The Skill-Action Architecture: Learning Abstract Action Embeddings for Reinforcement Learning

no code implementations1 Jan 2021 Chang Li, Dongjin Song, DaCheng Tao

Derived from a novel discovery that the SMDP option framework has an MDP equivalence, SA hierarchically extracts skills (abstract actions) from primary actions and explicitly encodes these knowledge into skill context vectors (embedding vectors).

Hierarchical Reinforcement Learning

Wasserstein Distributionally Robust Optimization: A Three-Player Game Framework

no code implementations1 Jan 2021 Zhuozhuo Tu, Shan You, Tao Huang, DaCheng Tao

Wasserstein distributionally robust optimization (DRO) has recently received significant attention in machine learning due to its connection to generalization, robustness and regularization.

Unsupervised Word Alignment via Cross-Lingual Contrastive Learning

no code implementations1 Jan 2021 Di wu, Liang Ding, Shuo Yang, DaCheng Tao

Recently, the performance of the neural word alignment models has exceeded that of statistical models.

Contrastive Learning Translation +1

Score-based Causal Discovery from Heterogeneous Data

no code implementations1 Jan 2021 Chenwei Ding, Biwei Huang, Mingming Gong, Kun Zhang, Tongliang Liu, DaCheng Tao

Most algorithms in causal discovery consider a single domain with a fixed distribution.

Causal Discovery

Adaptive Curriculum Learning

no code implementations ICCV 2021 Yajing Kong, Liu Liu, Jun Wang, DaCheng Tao

Therefore, in contrast to recent works using a fixed curriculum, we devise a new curriculum learning method, Adaptive Curriculum Learning (Adaptive CL), adapting the difficulty of examples to the current state of the model.

Curriculum Learning

Semantic Inference Network for Few-shot Streaming Label Learning

no code implementations1 Jan 2021 Zhen Wang, Liu Liu, Yiqun Duan, DaCheng Tao

In this work, we formulate and study few-shot streaming label learning (FSLL), which models emerging new labels with only a few annotated examples by utilizing the knowledge learned from past labels.

Meta-Learning Multi-Label Classification

Minimal Geometry-Distortion Constraint for Unsupervised Image-to-Image Translation

no code implementations1 Jan 2021 Jiaxian Guo, Jiachen Li, Mingming Gong, Huan Fu, Kun Zhang, DaCheng Tao

Unsupervised image-to-image (I2I) translation, which aims to learn a domain mapping function without paired data, is very challenging because the function is highly under-constrained.

Translation Unsupervised Image-To-Image Translation

Understanding and Improving Lexical Choice in Non-Autoregressive Translation

no code implementations ICLR 2021 Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, DaCheng Tao, Zhaopeng Tu

To this end, we introduce an extra Kullback-Leibler divergence term derived by comparing the lexical choice of NAT model and that embedded in the raw data.

Knowledge Distillation Translation

Robustness, Privacy, and Generalization of Adversarial Training

1 code implementation25 Dec 2020 Fengxiang He, Shaopeng Fu, Bohan Wang, DaCheng Tao

This measure can be approximate empirically by an asymptotically consistent empirical estimator, {\it empirical robustified intensity}.

Generalization Bounds

Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing

1 code implementation25 Dec 2020 Jun Yu, Hao Zhou, Yibing Zhan, DaCheng Tao

Essentially, DGCPN addresses the inaccurate similarity problem by exploring and exploiting the data's intrinsic relationships in a graph.

Quantization

A Survey on Vision Transformer

no code implementations23 Dec 2020 Kai Han, Yunhe Wang, Hanting Chen, Xinghao Chen, Jianyuan Guo, Zhenhua Liu, Yehui Tang, An Xiao, Chunjing Xu, Yixing Xu, Zhaohui Yang, Yiman Zhang, DaCheng Tao

Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism.

Image Classification

Progressive One-shot Human Parsing

1 code implementation22 Dec 2020 Haoyu He, Jing Zhang, Bhavani Thuraisingham, DaCheng Tao

In this paper, we devise a novel Progressive One-shot Parsing network (POPNet) to address two critical challenges , i. e., testing bias and small sizes.

Human Parsing Metric Learning +1

Recent advances in deep learning theory

no code implementations20 Dec 2020 Fengxiang He, DaCheng Tao

Deep learning is usually described as an experiment-driven field under continuous criticizes of lacking theoretical foundations.

Bayesian Inference Learning Theory

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

3 code implementations9 Dec 2020 Shaoli Huang, Xinchao Wang, DaCheng Tao

As the main discriminative information of a fine-grained image usually resides in subtle regions, methods along this line are prone to heavy label noise in fine-grained recognition.

Fine-Grained Image Classification Semantic Composition +1

Towards Defending Multiple Adversarial Perturbations via Gated Batch Normalization

no code implementations3 Dec 2020 Aishan Liu, Shiyu Tang, Xianglong Liu, Xinyun Chen, Lei Huang, Zhuozhuo Tu, Dawn Song, DaCheng Tao

To better understand this phenomenon, we propose the \emph{multi-domain} hypothesis, stating that different types of adversarial perturbations are drawn from different domains.

Domain Generalization via Entropy Regularization

1 code implementation NeurIPS 2020 Shanshan Zhao, Mingming Gong, Tongliang Liu, Huan Fu, DaCheng Tao

To arrive at this, some methods introduce a domain discriminator through adversarial learning to match the feature distributions in multiple source domains.

Domain Generalization

Fast Class-wise Updating for Online Hashing

no code implementations1 Dec 2020 Mingbao Lin, Rongrong Ji, Xiaoshuai Sun, Baochang Zhang, Feiyue Huang, Yonghong Tian, DaCheng Tao

To achieve fast online adaptivity, a class-wise updating method is developed to decompose the binary code learning and alternatively renew the hash functions in a class-wise fashion, which well addresses the burden on large amounts of training batches.

Auto Learning Attention

1 code implementation NeurIPS 2020 Benteng Ma, Jing Zhang, Yong Xia, DaCheng Tao

Attention modules have been demonstrated effective in strengthening the representation ability of a neural network via reweighting spatial or channel features or stacking both operations sequentially.

Image Classification Keypoint Detection +1

SIR: Self-supervised Image Rectification via Seeing the Same Scene from Multiple Different Lenses

no code implementations30 Nov 2020 Jinlong Fan, Jing Zhang, DaCheng Tao

However, the model may overfit the synthetic images and generalize not well on real-world fisheye images due to the limited universality of a specific distortion model and the lack of explicitly modeling the distortion and rectification process.

Rectification Self-Supervised Learning

Inter-layer Transition in Neural Architecture Search

1 code implementation30 Nov 2020 Benteng Ma, Jing Zhang, Yong Xia, DaCheng Tao

Differential Neural Architecture Search (NAS) methods represent the network architecture as a repetitive proxy directed acyclic graph (DAG) and optimize the network weights and architecture weights alternatively in a differential manner.

Neural Architecture Search

DUT: Learning Video Stabilization by Simply Watching Unstable Videos

2 code implementations30 Nov 2020 Yufei Xu, Jing Zhang, Stephen J. Maybank, DaCheng Tao

We propose a Deep Unsupervised Trajectory-based stabilization framework (DUT) in this paper.

Video Stabilization

Recent Progress in Appearance-based Action Recognition

no code implementations25 Nov 2020 Jack Humphreys, Zhe Chen, DaCheng Tao

Action recognition, which is formulated as a task to identify various human actions in a video, has attracted increasing interest from computer vision researchers due to its importance in various applications.

Action Recognition

Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting

1 code implementation12 Nov 2020 Zeke Xie, Fengxiang He, Shaopeng Fu, Issei Sato, DaCheng Tao, Masashi Sugiyama

Thus it motivates us to design a similar mechanism named {\it artificial neural variability} (ANV), which helps artificial neural networks learn some advantages from ``natural'' neural networks.

Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model

1 code implementation4 Nov 2020 Zheheng Jiang, Feixiang Zhou, Aite Zhao, Xin Li, Ling Li, DaCheng Tao, Xuelong Li, Huiyu Zhou

To address this problem, we here propose a novel multiview latent-attention and dynamic discriminative model that jointly learns view-specific and view-shared sub-structures, where the former captures unique dynamics of each view whilst the latter encodes the interaction between the views.

Context-Aware Cross-Attention for Non-Autoregressive Translation

1 code implementation COLING 2020 Liang Ding, Longyue Wang, Di wu, DaCheng Tao, Zhaopeng Tu

Non-autoregressive translation (NAT) significantly accelerates the inference process by predicting the entire target sequence.

Translation

Bridging Composite and Real: Towards End-to-end Deep Image Matting

1 code implementation30 Oct 2020 Jizhizi Li, Jing Zhang, Stephen J. Maybank, DaCheng Tao

Furthermore, we provide a benchmark containing 2, 000 high-resolution real-world animal images and 10, 000 portrait images along with their manually labeled alpha mattes to serve as a test bed for evaluating matting model's generalization ability on real-world images.

Image Matting Matting +1

Wide-angle Image Rectification: A Survey

1 code implementation30 Oct 2020 Jinlong Fan, Jing Zhang, Stephen J. Maybank, DaCheng Tao

In this paper, we comprehensively survey progress in wide-angle image rectification from transformation models to rectification methods.

3D Reconstruction Autonomous Driving +1

SCOP: Scientific Control for Reliable Neural Network Pruning

4 code implementations NeurIPS 2020 Yehui Tang, Yunhe Wang, Yixing Xu, DaCheng Tao, Chunjing Xu, Chao Xu, Chang Xu

To increase the reliability of the results, we prefer to have a more rigorous research design by including a scientific control group as an essential part to minimize the effect of all factors except the association between the filter and expected network output.

Network Pruning

Quantum circuit architecture search: error mitigation and trainability enhancement for variational quantum solvers

1 code implementation20 Oct 2020 Yuxuan Du, Tao Huang, Shan You, Min-Hsiu Hsieh, DaCheng Tao

Quantum error mitigation techniques are at the heart of quantum hardware implementation, and are the key to performance improvement of the variational quantum learning scheme (VQLS).

On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration

no code implementations16 Oct 2020 Zhihao Cheng, Liu Liu, Aishan Liu, Hao Sun, Meng Fang, DaCheng Tao

By contrast, this paper proves that LfO is almost equivalent to LfD in the deterministic robot environment, and more generally even in the robot environment with bounded randomness.

Imitation Learning

Learning Propagation Rules for Attribution Map Generation

no code implementations ECCV 2020 Yiding Yang, Jiayan Qiu, Mingli Song, DaCheng Tao, Xinchao Wang

Prior gradient-based attribution-map methods rely on handcrafted propagation rules for the non-linear/activation layers during the backward pass, so as to produce gradients of the input and then the attribution map.

Targeted Physical-World Attention Attack on Deep Learning Models in Road Sign Recognition

2 code implementations9 Oct 2020 Xinghao Yang, Weifeng Liu, Shengli Zhang, Wei Liu, DaCheng Tao

To alleviate these problems, this paper proposes the targeted attention attack (TAA) method for real world road sign attack.

Traffic Sign Recognition

Exposure Trajectory Recovery from Motion Blur

1 code implementation6 Oct 2020 Youjian Zhang, Chaoyue Wang, Stephen J. Maybank, DaCheng Tao

However, the motion information contained in a blurry image has yet to be fully explored and accurately formulated because: (i) the ground truth of dynamic motion is difficult to obtain; (ii) the temporal ordering is destroyed during the exposure; and (iii) the motion estimation from a blurry image is highly ill-posed.

Deblurring Image Deblurring +1

Open-Set Hypothesis Transfer with Semantic Consistency

no code implementations1 Oct 2020 Zeyu Feng, Chang Xu, DaCheng Tao

Unsupervised open-set domain adaptation (UODA) is a realistic problem where unlabeled target data contain unknown classes.

Domain Adaptation

Batch Coherence-Driven Network for Part-aware Person Re-Identification

no code implementations21 Sep 2020 Kan Wang, Pengfei Wang, Changxing Ding, DaCheng Tao

First, we introduce a batch coherence-guided channel attention (BCCA) module that highlights the relevant channels for each respective part from the output of a deep backbone model.

Person Re-Identification

AdderSR: Towards Energy Efficient Image Super-Resolution

no code implementations CVPR 2021 Dehua Song, Yunhe Wang, Hanting Chen, Chang Xu, Chunjing Xu, DaCheng Tao

To this end, we thoroughly analyze the relationship between an adder operation and the identity mapping and insert shortcuts to enhance the performance of SR models using adder networks.

Image Classification Image Super-Resolution

Heatmap Regression via Randomized Rounding

2 code implementations1 Sep 2020 Baosheng Yu, DaCheng Tao

Previous methods to overcome the sub-pixel localization problem usually rely on high-resolution heatmaps.

Face Alignment Pose Estimation +1

Adaptive Context-Aware Multi-Modal Network for Depth Completion

1 code implementation25 Aug 2020 Shanshan Zhao, Mingming Gong, Huan Fu, DaCheng Tao

Furthermore, considering the mutli-modality of input data, we exploit the graph propagation on the two modalities respectively to extract multi-modal representations.

Depth Completion

Nighttime Dehazing with a Synthetic Benchmark

1 code implementation10 Aug 2020 Jing Zhang, Yang Cao, Zheng-Jun Zha, DaCheng Tao

To address this issue, we propose a novel synthetic method called 3R to simulate nighttime hazy images from daytime clear images, which first reconstructs the scene geometry, then simulates the light rays and object reflectance, and finally renders the haze effects.

Recurrent Feature Reasoning for Image Inpainting

1 code implementation CVPR 2020 Jingyuan Li, Ning Wang, Lefei Zhang, Bo Du, DaCheng Tao

To capture information from distant places in the feature map for RFR, we further develop KCA and incorporate it in RFR.

Image Inpainting SSIM

Polysemy Deciphering Network for Robust Human-Object Interaction Detection

2 code implementations7 Aug 2020 Xubin Zhong, Changxing Ding, Xian Qu, DaCheng Tao

To address this issue, in this paper, we propose a novel Polysemy Deciphering Network (PD-Net) that decodes the visual polysemy of verbs for HOI detection in three distinct ways.

Human-Object Interaction Detection Scene Understanding

Approximated Bilinear Modules for Temporal Modeling

1 code implementation ICCV 2019 Xinqi Zhu, Chang Xu, Langwen Hui, Cewu Lu, DaCheng Tao

Specifically, we show how two-layer subnets in CNNs can be converted to temporal bilinear modules by adding an auxiliary-branch.

Action Recognition

Learning Disentangled Representations with Latent Variation Predictability

1 code implementation ECCV 2020 Xinqi Zhu, Chang Xu, DaCheng Tao

Given image pairs generated by latent codes varying in a single dimension, this varied dimension could be closely correlated with these image pairs if the representation is well disentangled.

Visual Compositional Learning for Human-Object Interaction Detection

4 code implementations ECCV 2020 Zhi Hou, Xiaojiang Peng, Yu Qiao, DaCheng Tao

The integration of decomposition and composition enables VCL to share object and verb features among different HOI samples and images, and to generate new interaction samples and new types of HOI, and thus largely alleviates the long-tail distribution problem and benefits low-shot or zero-shot HOI detection.

Human-Object Interaction Detection

Quantum differentially private sparse regression learning

no code implementations23 Jul 2020 Yuxuan Du, Min-Hsiu Hsieh, Tongliang Liu, Shan You, DaCheng Tao

The main contribution of this paper is devising a quantum DP Lasso estimator to earn the runtime speedup with the privacy preservation, i. e., the runtime complexity is $\tilde{O}(N^{3/2}\sqrt{d})$ with a nearly optimal utility bound $\tilde{O}(1/N^{2/3})$, where $N$ is the sample size and $d$ is the data dimension with $N\ll d$.

Symbiotic Adversarial Learning for Attribute-based Person Search

1 code implementation ECCV 2020 Yu-Tong Cao, Jingya Wang, DaCheng Tao

The current state-of-the-art methods either focus on learning better cross-modal embeddings by mining only seen data, or they explicitly use generative adversarial networks (GANs) to synthesize unseen features.

Person Search

Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms

no code implementations18 Jul 2020 Fengxiang He, Bohan Wang, DaCheng Tao

This paper studies the relationship between generalization and privacy preservation in iterative learning algorithms by two sequential steps.

Federated Learning Generalization Bounds

Quantum Geometric Machine Learning for Quantum Circuits and Control

1 code implementation19 Jun 2020 Elija Perrier, Christopher Ferrie, DaCheng Tao

Our results demonstrate how geometric control techniques can be used to both (a) verify the extent to which geometrically synthesised quantum circuits lie along geodesic, and thus time-optimal, routes and (b) synthesise those circuits.

Part-dependent Label Noise: Towards Instance-dependent Label Noise

1 code implementation NeurIPS 2020 Xiaobo Xia, Tongliang Liu, Bo Han, Nannan Wang, Mingming Gong, Haifeng Liu, Gang Niu, DaCheng Tao, Masashi Sugiyama

Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise.

Condensing Two-stage Detection with Automatic Object Key Part Discovery

1 code implementation10 Jun 2020 Zhe Chen, Jing Zhang, DaCheng Tao

Modern two-stage object detectors generally require excessively large models for their detection heads to achieve high accuracy.

Knowledge Distillation: A Survey

no code implementations9 Jun 2020 Jianping Gou, Baosheng Yu, Stephen John Maybank, DaCheng Tao

To this end, a variety of model compression and acceleration techniques have been developed.

Knowledge Distillation Model Compression +2

Boundary-assisted Region Proposal Networks for Nucleus Segmentation

1 code implementation4 Jun 2020 Shengcong Chen, Changxing Ding, DaCheng Tao

Accordingly, in this paper, we devise a Boundary-assisted Region Proposal Network (BRP-Net) that achieves robust instance-level nucleus segmentation.

Boundary Detection Instance Segmentation +2

DC-NAS: Divide-and-Conquer Neural Architecture Search

no code implementations29 May 2020 Yunhe Wang, Yixing Xu, DaCheng Tao

Neural architecture searching is a way of automatically exploring optimal deep neural networks in a given huge search space.

Neural Architecture Search

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

1 code implementation CVPR 2021 Zhaohui Yang, Yunhe Wang, Xinghao Chen, Jianyuan Guo, Wei zhang, Chao Xu, Chunjing Xu, DaCheng Tao, Chang Xu

To achieve an extremely fast NAS while preserving the high accuracy, we propose to identify the vital blocks and make them the priority in the architecture search.

Neural Architecture Search

Spatiotemporal Attacks for Embodied Agents

1 code implementation ECCV 2020 Aishan Liu, Tairan Huang, Xianglong Liu, Yitao Xu, Yuqing Ma, Xinyun Chen, Stephen J. Maybank, DaCheng Tao

Adversarial attacks are valuable for providing insights into the blind-spots of deep learning models and help improve their robustness.

Understanding Generalization in Recurrent Neural Networks

no code implementations ICLR 2020 Zhuozhuo Tu, Fengxiang He, DaCheng Tao

We first present a new generalization bound for recurrent neural networks based on matrix 1-norm and Fisher-Rao norm.

Generalization Bounds

Self-Attention with Cross-Lingual Position Representation

no code implementations ACL 2020 Liang Ding, Long-Yue Wang, DaCheng Tao

Position encoding (PE), an essential part of self-attention networks (SANs), is used to preserve the word order information for natural language processing tasks, generating fixed position indices for input sequences.

Machine Translation Translation

Deep Multimodal Neural Architecture Search

no code implementations25 Apr 2020 Zhou Yu, Yuhao Cui, Jun Yu, Meng Wang, DaCheng Tao, Qi Tian

Most existing works focus on a single task and design neural architectures manually, which are highly task-specific and hard to generalize to different tasks.

Neural Architecture Search Question Answering +3

Repulsive Mixture Models of Exponential Family PCA for Clustering

no code implementations7 Apr 2020 Maoying Qiao, Tongliang Liu, Jun Yu, Wei Bian, DaCheng Tao

To alleviate this problem, in this paper, a repulsiveness-encouraging prior is introduced among mixing components and a diversified EPCA mixture (DEPCAM) model is developed in the Bayesian framework.

Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach

no code implementations6 Apr 2020 Maoying Qiao, Jun Yu, Wei Bian, DaCheng Tao

Specifically, an HMRNet is reorganized into a hierarchical structure with homogeneous networks as its layers and heterogeneous links connecting them.

Community Detection

Learning Oracle Attention for High-fidelity Face Completion

no code implementations CVPR 2020 Tong Zhou, Changxing Ding, Shaowen Lin, Xinchao Wang, DaCheng Tao

While recent works adopted the attention mechanism to learn the contextual relations among elements of the face, they have largely overlooked the disastrous impacts of inaccurate attention scores; in addition, they fail to pay sufficient attention to key facial components, the completion results of which largely determine the authenticity of a face image.

Facial Inpainting

GPS-Net: Graph Property Sensing Network for Scene Graph Generation

1 code implementation CVPR 2020 Xin Lin, Changxing Ding, Jinquan Zeng, DaCheng Tao

There are three key properties of scene graph that have been underexplored in recent works: namely, the edge direction information, the difference in priority between nodes, and the long-tailed distribution of relationships.

Graph Generation Scene Graph Generation

Piecewise linear activations substantially shape the loss surfaces of neural networks

no code implementations ICLR 2020 Fengxiang He, Bohan Wang, DaCheng Tao

This result holds for any neural network with arbitrary depth and arbitrary piecewise linear activation functions (excluding linear functions) under most loss functions in practice.

Distilling Knowledge from Graph Convolutional Networks

1 code implementation CVPR 2020 Yiding Yang, Jiayan Qiu, Mingli Song, DaCheng Tao, Xinchao Wang

To enable the knowledge transfer from the teacher GCN to the student, we propose a local structure preserving module that explicitly accounts for the topological semantics of the teacher.

Knowledge Distillation Transfer Learning

Quantum noise protects quantum classifiers against adversaries

no code implementations20 Mar 2020 Yuxuan Du, Min-Hsiu Hsieh, Tongliang Liu, DaCheng Tao, Nana Liu

This robustness property is intimately connected with an important security concept called differential privacy which can be extended to quantum differential privacy.

General Classification

Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification

1 code implementation18 Mar 2020 Changxing Ding, Kan Wang, Pengfei Wang, DaCheng Tao

MPN has three key advantages: 1) it does not need to conduct body part detection in the inference stage; 2) its model is very compact and efficient for both training and testing; 3) in the training stage, it requires only coarse priors of body part locations, which are easy to obtain.

Multi-Task Learning Person Re-Identification

A Spatial-Temporal Attentive Network with Spatial Continuity for Trajectory Prediction

no code implementations13 Mar 2020 Beihao Xia, Conghao Wang, Qinmu Peng, Xinge You, DaCheng Tao

It remains challenging to automatically predict the multi-agent trajectory due to multiple interactions including agent to agent interaction and scene to agent interaction.

Trajectory Prediction

Towards Mixture Proportion Estimation without Irreducibility

no code implementations10 Feb 2020 Yu Yao, Tongliang Liu, Bo Han, Mingming Gong, Gang Niu, Masashi Sugiyama, DaCheng Tao

It is worthwhile to change the problem: we prove that if the assumption holds, our method will not affect anything; if the assumption does not hold, the bias from problem changing is less than the bias from violation of the irreducible assumption in the original problem.

On Positive-Unlabeled Classification in GAN

1 code implementation CVPR 2020 Tianyu Guo, Chang Xu, Jiajun Huang, Yunhe Wang, Boxin Shi, Chao Xu, DaCheng Tao

In contrast, it is more reasonable to treat the generated data as unlabeled, which could be positive or negative according to their quality.

General Classification

Towards High Performance Human Keypoint Detection

1 code implementation3 Feb 2020 Jing Zhang, Zhe Chen, DaCheng Tao

Human keypoint detection from a single image is very challenging due to occlusion, blur, illumination and scale variance.