Search Results for author: Jiashi Feng

Found 277 papers, 110 papers with code

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

no code implementations16 Mar 2023 Kunyang Han, Yong liu, Jun Hao Liew, Henghui Ding, Yunchao Wei, Jiajun Liu, Yitong Wang, Yansong Tang, Yujiu Yang, Jiashi Feng, Yao Zhao

Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred to as open-vocabulary semantic segmentation (OVS).

Knowledge Distillation Open Vocabulary Semantic Segmentation +3

Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring

1 code implementation26 Jan 2023 Ruyang Liu, Jingjia Huang, Ge Li, Jiashi Feng, Xinglong Wu, Thomas H. Li

In this paper, based on the CLIP model, we revisit temporal modeling in the context of image-to-video knowledge transferring, which is the key point for extending image-text pretrained models to the video domain.

Ranked #5 on Video Retrieval on MSR-VTT-1kA (using extra training data)

Representation Learning Retrieval +3

Temporal Perceiving Video-Language Pre-training

no code implementations18 Jan 2023 Fan Ma, Xiaojie Jin, Heng Wang, Jingjia Huang, Linchao Zhu, Jiashi Feng, Yi Yang

Specifically, text-video localization consists of moment retrieval, which predicts start and end boundaries in videos given the text description, and text localization which matches the subset of texts with the video features.

Contrastive Learning Moment Retrieval +7

CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition

no code implementations15 Jan 2023 Cheng-Ze Lu, Xiaojie Jin, Zhicheng Huang, Qibin Hou, Ming-Ming Cheng, Jiashi Feng

Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition.

Action Recognition Temporal Action Localization

Class Prototype-based Cleaner for Label Noise Learning

1 code implementation21 Dec 2022 Jingjia Huang, Yuanqi Chen, Jiashi Feng, Xinglong Wu

Semi-supervised learning based methods are current SOTA solutions to the noisy-label learning problem, which rely on learning an unsupervised label cleaner first to divide the training samples into a labeled set for clean data and an unlabeled set for noise data.

Image Classification

PV3D: A 3D Generative Model for Portrait Video Generation

no code implementations13 Dec 2022 Eric Zhongcong Xu, Jianfeng Zhang, Jun Hao Liew, Wenqing Zhang, Song Bai, Jiashi Feng, Mike Zheng Shou

While some prior works have applied such image GANs to unconditional 2D portrait video generation and static 3D portrait synthesis, there are few works successfully extending GANs for generating 3D-aware portrait videos.

Video Generation

Diffusion Probabilistic Model Made Slim

no code implementations27 Nov 2022 Xingyi Yang, Daquan Zhou, Jiashi Feng, Xinchao Wang

Despite the recent visually-pleasing results achieved, the massive computational cost has been a long-standing flaw for diffusion probabilistic models (DPMs), which, in turn, greatly limits their applications on resource-limited platforms.

Image Generation Unconditional Image Generation

AvatarGen: A 3D Generative Model for Animatable Human Avatars

1 code implementation26 Nov 2022 Jianfeng Zhang, Zihang Jiang, Dingdong Yang, Hongyi Xu, Yichun Shi, Guoxian Song, Zhongcong Xu, Xinchao Wang, Jiashi Feng

Specifically, we decompose the generative 3D human synthesis into pose-guided mapping and canonical representation with predefined human pose and shape, such that the canonical representation can be explicitly driven to different poses and shapes with the guidance of a 3D parametric human model SMPL.

Expanding Small-Scale Datasets with Guided Imagination

1 code implementation25 Nov 2022 Yifan Zhang, Daquan Zhou, Bryan Hooi, Kai Wang, Jiashi Feng

The two criteria are verified to be essential for effective dataset expansion: GIF-SD obtains 13. 5\% higher model accuracy on natural image datasets than unguided expansion with SD.

Zero-Shot Learning

Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition

1 code implementation22 Nov 2022 Qibin Hou, Cheng-Ze Lu, Ming-Ming Cheng, Jiashi Feng

This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features.

object-detection Object Detection +1

MagicVideo: Efficient Video Generation With Latent Diffusion Models

no code implementations20 Nov 2022 Daquan Zhou, Weimin WANG, Hanshu Yan, Weiwei Lv, Yizhe Zhu, Jiashi Feng

With the proposed efficient latent 3D U-Net design, MagicVideo can generate video clips with 256x256 spatial resolution on a single GPU card, which is 64x faster than the recent video diffusion model (VDM).

Text-to-Video Generation Video Generation

MagicMix: Semantic Mixing with Diffusion Models

1 code implementation28 Oct 2022 Jun Hao Liew, Hanshu Yan, Daquan Zhou, Jiashi Feng

Unlike style transfer, where an image is stylized according to the reference style without changing the image content, semantic blending mixes two different concepts in a semantic manner to synthesize a novel concept while preserving the spatial layout and geometry.

Denoising Style Transfer

Reachability-Aware Laplacian Representation in Reinforcement Learning

no code implementations24 Oct 2022 Kaixin Wang, Kuangqi Zhou, Jiashi Feng, Bryan Hooi, Xinchao Wang

In Reinforcement Learning (RL), Laplacian Representation (LapRep) is a task-agnostic state representation that encodes the geometry of the environment.

reinforcement-learning reinforcement Learning

MetaFormer Baselines for Vision

5 code implementations24 Oct 2022 Weihao Yu, Chenyang Si, Pan Zhou, Mi Luo, Yichen Zhou, Jiashi Feng, Shuicheng Yan, Xinchao Wang

By simply applying depthwise separable convolutions as token mixer in the bottom stages and vanilla self-attention in the top stages, the resulting model CAFormer sets a new record on ImageNet-1K: it achieves an accuracy of 85. 5% at 224x224 resolution, under normal supervised training without external data or distillation.

Ranked #57 on Image Classification on ImageNet (using extra training data)

Image Classification

Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning

1 code implementation17 Oct 2022 Dongze Lian, Daquan Zhou, Jiashi Feng, Xinchao Wang

With the proposed SSF, our model obtains 2. 46% (90. 72% vs. 88. 54%) and 11. 48% (73. 10% vs. 65. 57%) performance improvement on FGVC and VTAB-1k in terms of Top-1 accuracy compared to the full fine-tuning but only fine-tuning about 0. 3M parameters.

Image Classification

ManiCLIP: Multi-Attribute Face Manipulation from Text

no code implementations2 Oct 2022 Hao Wang, Guosheng Lin, Ana García del Molino, Anran Wang, Zehuan Yuan, Jiashi Feng

In this paper we present a novel multi-attribute face manipulation method based on textual descriptions.

Text-based Image Editing

Global Prototype Encoding for Incremental Video Highlights Detection

no code implementations12 Sep 2022 Sen Pei, Shixiong Xu, Ye Yuan, Jiashi Feng, Xiaohui Shen, Xiaojie Jin

To the best of our knowledge, this is the first time the incremental learning settings are introduced to video highlights detection, which in turn relieves the burden of training video inputs and promotes the scalability of conventional neural networks in proportion to both the size of the dataset and the quantity of domains.

Incremental Learning

AvatarGen: a 3D Generative Model for Animatable Human Avatars

1 code implementation1 Aug 2022 Jianfeng Zhang, Zihang Jiang, Dingdong Yang, Hongyi Xu, Yichun Shi, Guoxian Song, Zhongcong Xu, Xinchao Wang, Jiashi Feng

Unsupervised generation of clothed virtual humans with various appearance and animatable poses is important for creating 3D human avatars and other AR/VR applications.

3D Human Reconstruction

Contrastive Masked Autoencoders are Stronger Vision Learners

1 code implementation27 Jul 2022 Zhicheng Huang, Xiaojie Jin, Chengze Lu, Qibin Hou, Ming-Ming Cheng, Dongmei Fu, Xiaohui Shen, Jiashi Feng

The target encoder, fed with the full images, enhances the feature discriminability via contrastive learning with its online counterpart.

Contrastive Learning Image Classification +3

Clover: Towards A Unified Video-Language Alignment and Fusion Model

1 code implementation16 Jul 2022 Jingjia Huang, Yinan Li, Jiashi Feng, Xinglong Wu, Xiaoshuai Sun, Rongrong Ji

We then introduce \textbf{Clover}\textemdash a Correlated Video-Language pre-training method\textemdash towards a universal Video-Language model for solving multiple video understanding tasks with neither performance nor efficiency compromise.

Language Modelling Question Answering +10

Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

1 code implementation28 May 2022 Jianfei Yang, Xiangyu Peng, Kai Wang, Zheng Zhu, Jiashi Feng, Lihua Xie, Yang You

Domain Adaptation of Black-box Predictors (DABP) aims to learn a model on an unlabeled target domain supervised by a black-box predictor trained on a source domain.

Domain Adaptation Knowledge Distillation

Sharpness-Aware Training for Free

1 code implementation27 May 2022 Jiawei Du, Daquan Zhou, Jiashi Feng, Vincent Y. F. Tan, Joey Tianyi Zhou

Intuitively, SAF achieves this by avoiding sudden drops in the loss in the sharp local minima throughout the trajectory of the updates of the weights.

Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction

no code implementations23 May 2022 Kuangqi Zhou, Kaixin Wang, Jiashi Feng, Jian Tang, Tingyang Xu, Xinchao Wang

However, existing best deep AL methods are mostly developed for a single type of learning task (e. g., single-label classification), and hence may not perform well in molecular property prediction that involves various task types.

Active Learning Drug Discovery +1

Understanding The Robustness in Vision Transformers

1 code implementation26 Apr 2022 Daquan Zhou, Zhiding Yu, Enze Xie, Chaowei Xiao, Anima Anandkumar, Jiashi Feng, Jose M. Alvarez

Our study is motivated by the intriguing properties of the emerging visual grouping in Vision Transformers, which indicates that self-attention may promote robustness through improved mid-level representations.

Ranked #3 on Domain Generalization on ImageNet-C (using extra training data)

Domain Generalization Image Classification +3

Generalizing Few-Shot NAS with Gradient Matching

1 code implementation ICLR 2022 Shoukang Hu, Ruochen Wang, Lanqing Hong, Zhenguo Li, Cho-Jui Hsieh, Jiashi Feng

Efficient performance estimation of architectures drawn from large search spaces is essential to Neural Architecture Search.

Neural Architecture Search

PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision

1 code implementation CVPR 2022 Kehong Gong, Bingbing Li, Jianfeng Zhang, Tao Wang, Jing Huang, Michael Bi Mi, Jiashi Feng, Xinchao Wang

Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses.

3D Human Pose Estimation

SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations

1 code implementation15 Feb 2022 Tao Wang, Jun Hao Liew, Yu Li, Yunpeng Chen, Jiashi Feng

Unlike the original per grid cell object masks, SODAR is implicitly supervised to learn mask representations that encode geometric structure of nearby objects and complement adjacent representations with context.

Instance Segmentation Semantic Segmentation

The Geometry of Robust Value Functions

no code implementations30 Jan 2022 Kaixin Wang, Navdeep Kumar, Kuangqi Zhou, Bryan Hooi, Jiashi Feng, Shie Mannor

The key of this perspective is to decompose the value space, in a state-wise manner, into unions of hypersurfaces.

Towards Adversarially Robust Deep Image Denoising

no code implementations12 Jan 2022 Hanshu Yan, Jingfeng Zhang, Jiashi Feng, Masashi Sugiyama, Vincent Y. F. Tan

Secondly, to robustify DIDs, we propose an adversarial training strategy, hybrid adversarial training ({\sc HAT}), that jointly trains DIDs with adversarial and non-adversarial noisy data to ensure that the reconstruction quality is high and the denoisers around non-adversarial data are locally smooth.

Adversarial Attack Adversarial Robustness +1

UMAD: Universal Model Adaptation under Domain and Category Shift

no code implementations16 Dec 2021 Jian Liang, Dapeng Hu, Jiashi Feng, Ran He

To achieve bilateral adaptation in the target domain, we further maximize localized mutual information to align known samples with the source classifier and employ an entropic loss to push unknown samples far away from the source classification boundary, respectively.

Unsupervised Domain Adaptation

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning

1 code implementation CVPR 2022 Yujun Shi, Kuangqi Zhou, Jian Liang, Zihang Jiang, Jiashi Feng, Philip Torr, Song Bai, Vincent Y. F. Tan

Specifically, we experimentally show that directly encouraging CIL Learner at the initial phase to output similar representations as the model jointly trained on all classes can greatly boost the CIL performance.

Class Incremental Learning Incremental Learning

Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering

no code implementations8 Dec 2021 Mingfei Chen, Jianfeng Zhang, Xiangyu Xu, Lijuan Liu, Yujun Cai, Jiashi Feng, Shuicheng Yan

Meanwhile, for achieving higher rendering efficiency, we introduce a progressive rendering pipeline through geometry guidance, which leverages the geometric feature volume and the predicted density values to progressively reduce the number of sampling points and speed up the rendering process.

Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond

no code implementations NeurIPS 2021 Pan Zhou, Hanshu Yan, Xiaotong Yuan, Jiashi Feng, Shuicheng Yan

Specifically, we prove that lookahead using SGD as its inner-loop optimizer can better balance the optimization error and generalization error to achieve smaller excess risk error than vanilla SGD on (strongly) convex problems and nonconvex problems with Polyak-{\L}ojasiewicz condition which has been observed/proved in neural networks.

Shunted Self-Attention via Multi-Scale Token Aggregation

1 code implementation CVPR 2022 Sucheng Ren, Daquan Zhou, Shengfeng He, Jiashi Feng, Xinchao Wang

This novel merging scheme enables the self-attention to learn relationships between objects with different sizes and simultaneously reduces the token numbers and the computational cost.

MetaFormer Is Actually What You Need for Vision

12 code implementations CVPR 2022 Weihao Yu, Mi Luo, Pan Zhou, Chenyang Si, Yichen Zhou, Xinchao Wang, Jiashi Feng, Shuicheng Yan

Based on this observation, we hypothesize that the general architecture of the Transformers, instead of the specific token mixer module, is more essential to the model's performance.

Image Classification Object Detection +1

Direct Multi-view Multi-person 3D Pose Estimation

1 code implementation NeurIPS 2021 Tao Wang, Jianfeng Zhang, Yujun Cai, Shuicheng Yan, Jiashi Feng

Instead of estimating 3D joint locations from costly volumetric representation or reconstructing the per-person 3D pose from multiple detected 2D poses as in previous methods, MvP directly regresses the multi-person 3D poses in a clean and efficient way, without relying on intermediate tasks.

Ranked #3 on 3D Multi-Person Pose Estimation on Panoptic (using extra training data)

3D Multi-Person Pose Estimation 3D Pose Estimation

Deep Long-Tailed Learning: A Survey

1 code implementation9 Oct 2021 Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, Jiashi Feng

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution.

Efficient Sharpness-aware Minimization for Improved Training of Neural Networks

1 code implementation ICLR 2022 Jiawei Du, Hanshu Yan, Jiashi Feng, Joey Tianyi Zhou, Liangli Zhen, Rick Siow Mong Goh, Vincent Y. F. Tan

Recently, the relation between the sharpness of the loss landscape and the generalization error has been established by Foret et al. (2020), in which the Sharpness Aware Minimizer (SAM) was proposed to mitigate the degradation of the generalization.

How Well Does Self-Supervised Pre-Training Perform with Streaming ImageNet?

no code implementations NeurIPS Workshop ImageNet_PPF 2021 Dapeng Hu, Shipeng Yan, Qizhengqiu Lu, Lanqing Hong, Hailin Hu, Yifan Zhang, Zhenguo Li, Xinchao Wang, Jiashi Feng

Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained.

Self-Supervised Learning

PnP-DETR: Towards Efficient Visual Analysis with Transformers

1 code implementation ICCV 2021 Tao Wang, Li Yuan, Yunpeng Chen, Jiashi Feng, Shuicheng Yan

Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result.

object-detection Object Detection +1

Voxel Transformer for 3D Object Detection

1 code implementation ICCV 2021 Jiageng Mao, Yujing Xue, Minzhe Niu, Haoyue Bai, Jiashi Feng, Xiaodan Liang, Hang Xu, Chunjing Xu

We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds.

Ranked #3 on 3D Object Detection on waymo vehicle (L1 mAP metric)

3D Object Detection object-detection +1

Triplet Contrastive Learning for Brain Tumor Classification

no code implementations8 Aug 2021 Tian Yu Liu, Jiashi Feng

Brain tumor is a common and fatal form of cancer which affects both adults and children.

Classification Contrastive Learning +2

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

2 code implementations20 Jul 2021 Yifan Zhang, Bryan Hooi, Lanqing Hong, Jiashi Feng

Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution.

Image Classification Long-tail Learning

Recovering the Unbiased Scene Graphs from the Biased Ones

1 code implementation5 Jul 2021 Meng-Jiun Chiou, Henghui Ding, Hanshu Yan, Changhu Wang, Roger Zimmermann, Jiashi Feng

Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects.

Scene Graph Classification Scene Graph Detection +2

VOLO: Vision Outlooker for Visual Recognition

5 code implementations24 Jun 2021 Li Yuan, Qibin Hou, Zihang Jiang, Jiashi Feng, Shuicheng Yan

Though recently the prevailing vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification, their performance is still inferior to that of the latest SOTA CNNs if no extra data are provided.

Image Classification Semantic Segmentation

Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition

2 code implementations23 Jun 2021 Qibin Hou, Zihang Jiang, Li Yuan, Ming-Ming Cheng, Shuicheng Yan, Jiashi Feng

By realizing the importance of the positional information carried by 2D feature representations, unlike recent MLP-like models that encode the spatial information along the flattened spatial dimensions, Vision Permutator separately encodes the feature representations along the height and width dimensions with linear projections.

LV-BERT: Exploiting Layer Variety for BERT

1 code implementation Findings (ACL) 2021 Weihao Yu, Zihang Jiang, Fei Chen, Qibin Hou, Jiashi Feng

In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by exploiting layer variety from two aspects: the layer type set and the layer order.

No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data

no code implementations NeurIPS 2021 Mi Luo, Fei Chen, Dapeng Hu, Yifan Zhang, Jian Liang, Jiashi Feng

Motivated by the above findings, we propose a novel and simple algorithm called Classifier Calibration with Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated gaussian mixture model.

Classifier calibration Federated Learning

Refiner: Refining Self-attention for Vision Transformers

1 code implementation7 Jun 2021 Daquan Zhou, Yujun Shi, Bingyi Kang, Weihao Yu, Zihang Jiang, Yuan Li, Xiaojie Jin, Qibin Hou, Jiashi Feng

Vision Transformers (ViTs) have shown competitive accuracy in image classification tasks compared with CNNs.

Image Classification

Image-to-Video Generation via 3D Facial Dynamics

no code implementations31 May 2021 Xiaoguang Tu, Yingtian Zou, Jian Zhao, Wenjie Ai, Jian Dong, Yuan YAO, Zhikang Wang, Guodong Guo, Zhifeng Li, Wei Liu, Jiashi Feng

Video generation from a single face image is an interesting problem and usually tackled by utilizing Generative Adversarial Networks (GANs) to integrate information from the input face image and a sequence of sparse facial landmarks.

Image to Video Generation Video Prediction

PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal

1 code implementation26 May 2021 Si Liu, Wentao Jiang, Chen Gao, Ran He, Jiashi Feng, Bo Li, Shuicheng Yan

In this paper, we address the makeup transfer and removal tasks simultaneously, which aim to transfer the makeup from a reference image to a source image and remove the makeup from the with-makeup image respectively.

Style Transfer

Joint Face Image Restoration and Frontalization for Recognition

no code implementations12 May 2021 Xiaoguang Tu, Jian Zhao, Qiankun Liu, Wenjie Ai, Guodong Guo, Zhifeng Li, Wei Liu, Jiashi Feng

First, MDFR is a well-designed encoder-decoder architecture which extracts feature representation from an input face image with arbitrary low-quality factors and restores it to a high-quality counterpart.

Face Recognition Image Restoration

PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation

1 code implementation CVPR 2021 Kehong Gong, Jianfeng Zhang, Jiashi Feng

To address this problem, we present PoseAug, a new auto-augmentation framework that learns to augment the available training poses towards a greater diversity and thus improve generalization of the trained 2D-to-3D pose estimator.

 Ranked #1 on Monocular 3D Human Pose Estimation on Human3.6M (Use Video Sequence metric)

Data Augmentation Monocular 3D Human Pose Estimation +1

Body Meshes as Points

1 code implementation CVPR 2021 Jianfeng Zhang, Dongdong Yu, Jun Hao Liew, Xuecheng Nie, Jiashi Feng

In this work, we present a single-stage model, Body Meshes as Points (BMP), to simplify the pipeline and lift both efficiency and performance.

3D Human Shape Estimation 3D Multi-Person Pose Estimation +1

How Well Does Self-Supervised Pre-Training Perform with Streaming Data?

no code implementations ICLR 2022 Dapeng Hu, Shipeng Yan, Qizhengqiu Lu, Lanqing Hong, Hailin Hu, Yifan Zhang, Zhenguo Li, Xinchao Wang, Jiashi Feng

Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained.

Representation Learning Self-Supervised Learning

DINE: Domain Adaptation from Single and Multiple Black-box Predictors

3 code implementations CVPR 2022 Jian Liang, Dapeng Hu, Jiashi Feng, Ran He

To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (target).

Transductive Learning Unsupervised Domain Adaptation

Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation

no code implementations30 Mar 2021 Shuning Chang, Pichao Wang, Fan Wang, Hao Li, Jiashi Feng

Temporal action proposal generation (TAPG) is a fundamental and challenging task in video understanding, especially in temporal action detection.

Action Detection Temporal Action Proposal Generation +1

AutoSpace: Neural Architecture Search with Less Human Interference

1 code implementation ICCV 2021 Daquan Zhou, Xiaojie Jin, Xiaochen Lian, Linjie Yang, Yujing Xue, Qibin Hou, Jiashi Feng

Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction.

Neural Architecture Search

DeepViT: Towards Deeper Vision Transformer

4 code implementations22 Mar 2021 Daquan Zhou, Bingyi Kang, Xiaojie Jin, Linjie Yang, Xiaochen Lian, Zihang Jiang, Qibin Hou, Jiashi Feng

In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the performance of ViTs saturate fast when scaled to be deeper.

Image Classification Representation Learning

Coordinate Attention for Efficient Mobile Network Design

1 code implementation CVPR 2021 Qibin Hou, Daquan Zhou, Jiashi Feng

Recent studies on mobile network design have demonstrated the remarkable effectiveness of channel attention (e. g., the Squeeze-and-Excitation attention) for lifting model performance, but they generally neglect the positional information, which is important for generating spatially selective attention maps.

object-detection Object Detection +1

Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

1 code implementation NeurIPS 2021 Yifan Zhang, Bryan Hooi, Dapeng Hu, Jian Liang, Jiashi Feng

In this paper, we investigate whether applying contrastive learning to fine-tuning would bring further benefits, and analytically find that optimizing the contrastive loss benefits both discriminative representation learning and model optimization during fine-tuning.

Contrastive Learning Image Classification +4

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection

2 code implementations10 Feb 2021 Hanshu Yan, Jingfeng Zhang, Gang Niu, Jiashi Feng, Vincent Y. F. Tan, Masashi Sugiyama

By comparing \textit{non-robust} (normally trained) and \textit{robustified} (adversarially trained) models, we observe that adversarial training (AT) robustifies CNNs by aligning the channel-wise activations of adversarial data with those of their natural counterparts.

Adversarial Robustness

Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

12 code implementations ICCV 2021 Li Yuan, Yunpeng Chen, Tao Wang, Weihao Yu, Yujun Shi, Zihang Jiang, Francis EH Tay, Jiashi Feng, Shuicheng Yan

To overcome such limitations, we propose a new Tokens-To-Token Vision Transformer (T2T-ViT), which incorporates 1) a layer-wise Tokens-to-Token (T2T) transformation to progressively structurize the image to tokens by recursively aggregating neighboring Tokens into one Token (Tokens-to-Token), such that local structure represented by surrounding tokens can be modeled and tokens length can be reduced; 2) an efficient backbone with a deep-narrow structure for vision transformer motivated by CNN architecture design after empirical study.

Image Classification Language Modelling

ORDNet: Capturing Omni-Range Dependencies for Scene Parsing

no code implementations11 Jan 2021 Shaofei Huang, Si Liu, Tianrui Hui, Jizhong Han, Bo Li, Jiashi Feng, Shuicheng Yan

Our ORDNet is able to extract more comprehensive context information and well adapt to complex spatial variance in scene images.

Scene Parsing

DiffAutoML: Differentiable Joint Optimization for Efficient End-to-End Automated Machine Learning

no code implementations1 Jan 2021 Kaichen Zhou, Lanqing Hong, Fengwei Zhou, Binxin Ru, Zhenguo Li, Trigoni Niki, Jiashi Feng

Our method performs co-optimization of the neural architectures, training hyper-parameters and data augmentation policies in an end-to-end fashion without the need of model retraining.

BIG-bench Machine Learning Data Augmentation +1

Exploring Balanced Feature Spaces for Representation Learning

no code implementations ICLR 2021 Bingyi Kang, Yu Li, Sa Xie, Zehuan Yuan, Jiashi Feng

Motivated by this question, we conduct a series of studies on the performance of self-supervised contrastive learning and supervised learning methods over multiple datasets where training instance distributions vary from a balanced one to a long-tailed one.

Contrastive Learning Long-tail Learning +2

AggMask: Exploring locally aggregated learning of mask representations for instance segmentation

1 code implementation1 Jan 2021 Tao Wang, Jun Hao Liew, Yu Li, Yunpeng Chen, Jiashi Feng

Recently proposed one-stage instance segmentation models (\emph{e. g.}, SOLO) learn to directly predict location-specific object mask with fully-convolutional networks.

Instance Segmentation Semantic Segmentation

Learning Safe Policies with Cost-sensitive Advantage Estimation

no code implementations1 Jan 2021 Bingyi Kang, Shie Mannor, Jiashi Feng

Reinforcement Learning (RL) with safety guarantee is critical for agents performing tasks in risky environments.

Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer

1 code implementation14 Dec 2020 Jian Liang, Dapeng Hu, Yunbo Wang, Ran He, Jiashi Feng

Furthermore, we propose a new labeling transfer strategy, which separates the target data into two splits based on the confidence of predictions (labeling information), and then employ semi-supervised learning to improve the accuracy of less-confident predictions in the target domain.

Classification General Classification +3

Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts

1 code implementation NeurIPS 2020 Guilin Li, Junlei Zhang, Yunhe Wang, Chuanjian Liu, Matthias Tan, Yunfeng Lin, Wei zhang, Jiashi Feng, Tong Zhang

In particular, we propose a novel joint-training framework to train plain CNN by leveraging the gradients of the ResNet counterpart.

Fooling the primate brain with minimal, targeted image manipulation

no code implementations11 Nov 2020 Li Yuan, Will Xiao, Giorgia Dellaferrera, Gabriel Kreiman, Francis E. H. Tay, Jiashi Feng, Margaret S. Livingstone

Here we propose an array of methods for creating minimal, targeted image perturbations that lead to changes in both neuronal activity and perception as reflected in behavior.

Adversarial Attack Image Manipulation

Improving Generalization in Reinforcement Learning with Mixture Regularization

1 code implementation NeurIPS 2020 Kaixin Wang, Bingyi Kang, Jie Shao, Jiashi Feng

Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments.

Data Augmentation reinforcement-learning +1

Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes

no code implementations16 Oct 2020 Li Yuan, Yichen Zhou, Shuning Chang, Ziyuan Huang, Yunpeng Chen, Xuecheng Nie, Tao Wang, Jiashi Feng, Shuicheng Yan

Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing information of the scenes; (2) lacking training data in the crowd and complex scenes.

Action Recognition In Videos Semantic Segmentation

A Simple Baseline for Pose Tracking in Videos of Crowded Scenes

no code implementations16 Oct 2020 Li Yuan, Shuning Chang, Ziyuan Huang, Yichen Zhou, Yunpeng Chen, Xuecheng Nie, Francis E. H. Tay, Jiashi Feng, Shuicheng Yan

This paper presents our solution to ACM MM challenge: Large-scale Human-centric Video Analysis in Complex Events\cite{lin2020human}; specifically, here we focus on Track3: Crowd Pose Tracking in Complex Events.

Multi-Object Tracking Optical Flow Estimation +1

Towards Accurate Human Pose Estimation in Videos of Crowded Scenes

no code implementations16 Oct 2020 Li Yuan, Shuning Chang, Xuecheng Nie, Ziyuan Huang, Yichen Zhou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan

In this paper, we focus on improving human pose estimation in videos of crowded scenes from the perspectives of exploiting temporal context and collecting new data.

Optical Flow Estimation Pose Estimation

Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning

no code implementations NeurIPS 2020 Pan Zhou, Jiashi Feng, Chao Ma, Caiming Xiong, Steven Hoi, Weinan E

The result shows that (1) the escaping time of both SGD and ADAM~depends on the Radon measure of the basin positively and the heaviness of gradient noise negatively; (2) for the same basin, SGD enjoys smaller escaping time than ADAM, mainly because (a) the geometry adaptation in ADAM~via adaptively scaling each gradient coordinate well diminishes the anisotropic structure in gradient noise and results in larger Radon measure of a basin; (b) the exponential gradient average in ADAM~smooths its gradient and leads to lighter gradient noise tails than SGD.

Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations

1 code implementation10 Sep 2020 Meng-Jiun Chiou, Roger Zimmermann, Jiashi Feng

Visual relationship detection aims to reason over relationships among salient objects in images, which has drawn increasing attention over the past few years.

object-detection Object Detection +2

Dual Adversarial Auto-Encoders for Clustering

no code implementations23 Aug 2020 Pengfei Ge, Chuan-Xian Ren, Jiashi Feng, Shuicheng Yan

By performing variational inference on the objective function of Dual-AAE, we derive a new reconstruction loss which can be optimized by training a pair of Auto-encoders.

Variational Inference

ConvBERT: Improving BERT with Span-based Dynamic Convolution

7 code implementations NeurIPS 2020 Zi-Hang Jiang, Weihao Yu, Daquan Zhou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan

The novel convolution heads, together with the rest self-attention heads, form a new mixed attention block that is more efficient at both global and local context learning.

Natural Language Understanding

Few-shot Classification via Adaptive Attention

1 code implementation6 Aug 2020 Zi-Hang Jiang, Bingyi Kang, Kuangqi Zhou, Jiashi Feng

To be specific, we devise a simple and efficient meta-reweighting strategy to adapt the sample representations and generate soft attention to refine the representation such that the relevant features from the query and support samples can be extracted for a better few-shot classification.

Classification Few-Shot Learning +1

The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation

1 code implementation ECCV 2020 Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Junhao Liew, Sheng Tang, Steven Hoi, Jiashi Feng

Specifically, we systematically investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveil that a major cause is the inaccurate classification of object proposals.

General Classification Instance Segmentation +3

Domain Adaptation with Auxiliary Target Domain-Oriented Classifier

2 code implementations CVPR 2021 Jian Liang, Dapeng Hu, Jiashi Feng

ATDOC alleviates the classifier bias by introducing an auxiliary classifier for target data only, to improve the quality of pseudo labels.

Domain Adaptation Transfer Learning

Rethinking Bottleneck Structure for Efficient Mobile Network Design

4 code implementations ECCV 2020 Zhou Daquan, Qibin Hou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan

In this paper, we rethink the necessity of such design changes and find it may bring risks of information loss and gradient confusion.

General Classification Neural Architecture Search +2

Local Grid Rendering Networks for 3D Object Detection in Point Clouds

no code implementations4 Jul 2020 Jianan Li, Jiashi Feng

The performance of 3D object detection models over point clouds highly depends on their capability of modeling local geometric patterns.

3D Object Detection object-detection

Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation

no code implementations NeurIPS 2020 Jianfeng Zhang, Xuecheng Nie, Jiashi Feng

In this work, we propose a novel framework, Inference Stage Optimization (ISO), for improving the generalizability of 3D pose models when source and target data come from different pose distributions.

3D Human Pose Estimation Self-Supervised Learning

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

2 code implementations CVPR 2020 Yu Li, Tao Wang, Bingyi Kang, Sheng Tang, Chunfeng Wang, Jintao Li, Jiashi Feng

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution.

Image Classification Instance Segmentation +4

Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation

no code implementations14 Jun 2020 Kuangqi Zhou, Qibin Hou, Zun Li, Jiashi Feng

In this paper, we propose a novel multi-miner framework to perform a region mining process that adapts to diverse object sizes and is thus able to mine more integral and finer object regions.

Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Understanding and Resolving Performance Degradation in Graph Convolutional Networks

1 code implementation12 Jun 2020 Kuangqi Zhou, Yanfei Dong, Kaixin Wang, Wee Sun Lee, Bryan Hooi, Huan Xu, Jiashi Feng

In this work, we study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works.

Boosting Few-Shot Learning With Adaptive Margin Loss

no code implementations CVPR 2020 Aoxue Li, Weiran Huang, Xu Lan, Jiashi Feng, Zhenguo Li, Li-Wei Wang

Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples.

Few-Shot Image Classification Few-Shot Learning +2

Semantic Domain Adversarial Networks for Unsupervised Domain Adaptation

1 code implementation30 Mar 2020 Dapeng Hu, Jian Liang, Qibin Hou, Hanshu Yan, Yunpeng Chen, Shuicheng Yan, Jiashi Feng

To successfully align the multi-modal data structures across domains, the following works exploit discriminative information in the adversarial training process, e. g., using multiple class-wise discriminators and introducing conditional information in input or output of the domain discriminator.

Object Recognition Semantic Segmentation +1

Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

2 code implementations CVPR 2020 Qibin Hou, Li Zhang, Ming-Ming Cheng, Jiashi Feng

Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing.

Scene Parsing Semantic Segmentation

Cross-layer Feature Pyramid Network for Salient Object Detection

no code implementations25 Feb 2020 Zun Li, Congyan Lang, Junhao Liew, Qibin Hou, Yidong Li, Jiashi Feng

Feature pyramid network (FPN) based models, which fuse the semantics and salient details in a progressive manner, have been proven highly effective in salient object detection.

object-detection RGB Salient Object Detection +1

ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning

1 code implementation ICLR 2020 Weihao Yu, Zi-Hang Jiang, Yanfei Dong, Jiashi Feng

Empirical results show that state-of-the-art models have an outstanding ability to capture biases contained in the dataset with high accuracy on EASY set.

Logical Reasoning Logical Reasoning Question Answering +2

The Alzheimer's Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge: Results after 1 Year Follow-up

4 code implementations9 Feb 2020 Razvan V. Marinescu, Neil P. Oxtoby, Alexandra L. Young, Esther E. Bron, Arthur W. Toga, Michael W. Weiner, Frederik Barkhof, Nick C. Fox, Arman Eshaghi, Tina Toni, Marcin Salaterski, Veronika Lunina, Manon Ansart, Stanley Durrleman, Pascal Lu, Samuel Iddi, Dan Li, Wesley K. Thompson, Michael C. Donohue, Aviv Nahon, Yarden Levy, Dan Halbersberg, Mariya Cohen, Huiling Liao, Tengfei Li, Kaixian Yu, Hongtu Zhu, Jose G. Tamez-Pena, Aya Ismail, Timothy Wood, Hector Corrada Bravo, Minh Nguyen, Nanbo Sun, Jiashi Feng, B. T. Thomas Yeo, Gang Chen, Ke Qi, Shiyang Chen, Deqiang Qiu, Ionut Buciuman, Alex Kelner, Raluca Pop, Denisa Rimocea, Mostafa M. Ghazi, Mads Nielsen, Sebastien Ourselin, Lauge Sorensen, Vikram Venkatraghavan, Keli Liu, Christina Rabe, Paul Manser, Steven M. Hill, James Howlett, Zhiyue Huang, Steven Kiddle, Sach Mukherjee, Anais Rouanet, Bernd Taschler, Brian D. M. Tom, Simon R. White, Noel Faux, Suman Sedai, Javier de Velasco Oriol, Edgar E. V. Clemente, Karol Estrada, Leon Aksman, Andre Altmann, Cynthia M. Stonnington, Yalin Wang, Jianfeng Wu, Vivek Devadas, Clementine Fourrier, Lars Lau Raket, Aristeidis Sotiras, Guray Erus, Jimit Doshi, Christos Davatzikos, Jacob Vogel, Andrew Doyle, Angela Tam, Alex Diaz-Papkovich, Emmanuel Jammeh, Igor Koval, Paul Moore, Terry J. Lyons, John Gallacher, Jussi Tohka, Robert Ciszek, Bruno Jedynak, Kruti Pandya, Murat Bilgel, William Engels, Joseph Cole, Polina Golland, Stefan Klein, Daniel C. Alexander

TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease.

alzheimer's disease detection Disease Prediction

MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection

no code implementations22 Jan 2020 Mi Luo, Fei Chen, Pengxiang Cheng, Zhenhua Dong, Xiuqiang He, Jiashi Feng, Zhenguo Li

Recommender systems often face heterogeneous datasets containing highly personalized historical data of users, where no single model could give the best recommendation for every user.

Meta-Learning Model Selection +1

RC-DARTS: Resource Constrained Differentiable Architecture Search

no code implementations30 Dec 2019 Xiaojie Jin, Jiang Wang, Joshua Slocum, Ming-Hsuan Yang, Shengyang Dai, Shuicheng Yan, Jiashi Feng

In this paper, we propose the resource constrained differentiable architecture search (RC-DARTS) method to learn architectures that are significantly smaller and faster while achieving comparable accuracy.

Image Classification One-Shot Learning

Zoom in to where it matters: a hierarchical graph based model for mammogram analysis

no code implementations16 Dec 2019 Hao Du, Jiashi Feng, Mengling Feng

In clinical practice, human radiologists actually review medical images with high resolution monitors and zoom into region of interests (ROIs) for a close-up examination.

Classification General Classification +3

Efficient Meta Learning via Minibatch Proximal Update

no code implementations NeurIPS 2019 Pan Zhou, Xiao-Tong Yuan, Huan Xu, Shuicheng Yan, Jiashi Feng

We address the problem of meta-learning which learns a prior over hypothesis from a sample of meta-training tasks for fast adaptation on meta-testing tasks.

Few-Shot Learning

Classification Calibration for Long-tail Instance Segmentation

1 code implementation29 Oct 2019 Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Jun Hao Liew, Sheng Tang, Steven Hoi, Jiashi Feng

In this report, we investigate the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS [5] dataset, and find a major cause is the inaccurate classification of object proposals.

Classification General Classification +2

On Robustness of Neural Ordinary Differential Equations

2 code implementations ICLR 2020 Hanshu Yan, Jiawei Du, Vincent Y. F. Tan, Jiashi Feng

We then provide an insightful understanding of this phenomenon by exploiting a certain desirable property of the flow of a continuous-time ODE, namely that integral curves are non-intersecting.

Adversarial Attack

Compressed Video Action Recognition with Refined Motion Vector

no code implementations6 Oct 2019 Haoyuan Cao, Shining Yu, Jiashi Feng

Although CNN has reached satisfactory performance in image-related tasks, using CNN to process videos is much more challenging due to the enormous size of raw video streams.

Action Recognition Optical Flow Estimation +2

Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning

1 code implementation27 Sep 2019 Mingjie Sun, Jimin Xiao, Eng Gee Lim, Yanchu Xie, Jiashi Feng

In this paper, we aim to tackle the task of semi-supervised video object segmentation across a sequence of frames where only the ground-truth segmentation of the first frame is provided.

reinforcement-learning reinforcement Learning +3

Hierarchical Neural Architecture Search via Operator Clustering

1 code implementation26 Sep 2019 Guilin Li, Xing Zhang, Zitong Wang, Matthias Tan, Jiashi Feng, Zhenguo Li, Tong Zhang

Recently, the efficiency of automatic neural architecture design has been significantly improved by gradient-based search methods such as DARTS.

Neural Architecture Search

Towards Disentangling Non-Robust and Robust Components in Performance Metric

no code implementations25 Sep 2019 Yujun Shi, Benben Liao, Guangyong Chen, Yun Liu, Ming-Ming Cheng, Jiashi Feng

Then, we show by experiments that DNNs under standard training rely heavily on optimizing the non-robust component in achieving decent performance.

Adversarial Robustness

Prototype Recalls for Continual Learning

no code implementations25 Sep 2019 Mengmi Zhang, Tao Wang, Joo Hwee Lim, Jiashi Feng

Without tampering with the performance on initial tasks, our method learns novel concepts given a few training examples of each class in new tasks.

Continual Learning Metric Learning +1

Revisiting Knowledge Distillation via Label Smoothing Regularization

2 code implementations CVPR 2020 Li Yuan, Francis E. H. Tay, Guilin Li, Tao Wang, Jiashi Feng

Without any extra computation cost, Tf-KD achieves up to 0. 65\% improvement on ImageNet over well-established baseline models, which is superior to label smoothing regularization.

Self-Knowledge Distillation

PROTOTYPE-ASSISTED ADVERSARIAL LEARNING FOR UNSUPERVISED DOMAIN ADAPTATION

no code implementations25 Sep 2019 Dapeng Hu, Jian Liang*, Qibin Hou, Hanshu Yan, Jiashi Feng

Previous adversarial learning methods condition domain alignment only on pseudo labels, but noisy and inaccurate pseudo labels may perturb the multi-class distribution embedded in probabilistic predictions, hence bringing insufficient alleviation to the latent mismatch problem.

Object Recognition Semantic Segmentation +1

Hierarchic Neighbors Embedding

no code implementations16 Sep 2019 Shenglan Liu, Yang Yu, Yang Liu, Hong Qiao, Lin Feng, Jiashi Feng

Manifold learning now plays a very important role in machine learning and many relevant applications.

PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer

1 code implementation CVPR 2020 Wentao Jiang, Si Liu, Chen Gao, Jie Cao, Ran He, Jiashi Feng, Shuicheng Yan

In this paper, we address the makeup transfer task, which aims to transfer the makeup from a reference image to a source image.

Dynamic Kernel Distillation for Efficient Pose Estimation in Videos

no code implementations ICCV 2019 Xuecheng Nie, Yuncheng Li, Linjie Luo, Ning Zhang, Jiashi Feng

Existing video-based human pose estimation methods extensively apply large networks onto every frame in the video to localize body joints, which suffer high computational cost and hardly meet the low-latency requirement in realistic applications.

2D Human Pose Estimation Pose Estimation

Single-Stage Multi-Person Pose Machines

1 code implementation ICCV 2019 Xuecheng Nie, Jianfeng Zhang, Shuicheng Yan, Jiashi Feng

Based on SPR, we develop the SPM model that can directly predict structured poses for multiple persons in a single stage, and thus offer a more compact pipeline and attractive efficiency advantage over two-stage methods.

3D Pose Estimation Keypoint Detection +1

PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

5 code implementations ICCV 2019 Kaixin Wang, Jun Hao Liew, Yingtian Zou, Daquan Zhou, Jiashi Feng

In this paper, we tackle the challenging few-shot segmentation problem from a metric learning perspective and present PANet, a novel prototype alignment network to better utilize the information of the support set.

Few-Shot Semantic Segmentation Metric Learning +1

Central Similarity Quantization for Efficient Image and Video Retrieval

1 code implementation CVPR 2020 Li Yuan, Tao Wang, Xiaopeng Zhang, Francis EH Tay, Zequn Jie, Wei Liu, Jiashi Feng

In this work, we propose a new \emph{global} similarity metric, termed as \emph{central similarity}, with which the hash codes of similar data pairs are encouraged to approach a common center and those for dissimilar pairs to converge to different centers, to improve hash learning efficiency and retrieval accuracy.

Quantization Retrieval +1

Neural Epitome Search for Architecture-Agnostic Network Compression

no code implementations ICLR 2020 Daquan Zhou, Xiaojie Jin, Qibin Hou, Kaixin Wang, Jianchao Yang, Jiashi Feng

The recent WSNet [1] is a new model compression method through sampling filterweights from a compact set and has demonstrated to be effective for 1D convolutionneural networks (CNNs).

Model Compression Neural Architecture Search

Delving into 3D Action Anticipation from Streaming Videos

no code implementations15 Jun 2019 Hongsong Wang, Jiashi Feng

Action anticipation, which aims to recognize the action with a partial observation, becomes increasingly popular due to a wide range of applications.

Action Anticipation Action Classification +1

PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction

1 code implementation15 Jun 2019 Hongsong Wang, Jian Dong, Bin Cheng, Jiashi Feng

We therefore propose a novel Position-Velocity Recurrent Encoder-Decoder (PVRED) for human motion prediction, which makes full use of pose velocities and temporal positional information.

Human motion prediction motion prediction

Distilling Object Detectors with Fine-grained Feature Imitation

3 code implementations CVPR 2019 Tao Wang, Li Yuan, Xiaopeng Zhang, Jiashi Feng

To address the challenge of distilling knowledge in detection model, we propose a fine-grained feature imitation method exploiting the cross-location discrepancy of feature response.

Knowledge Distillation object-detection +1

Understanding Adversarial Behavior of DNNs by Disentangling Non-Robust and Robust Components in Performance Metric

no code implementations6 Jun 2019 Yujun Shi, Benben Liao, Guangyong Chen, Yun Liu, Ming-Ming Cheng, Jiashi Feng

Despite many previous works studying the reason behind such adversarial behavior, the relationship between the generalization performance and adversarial behavior of DNNs is still little understood.

Adversarial Robustness

Query-efficient Meta Attack to Deep Neural Networks

1 code implementation ICLR 2020 Jiawei Du, Hu Zhang, Joey Tianyi Zhou, Yi Yang, Jiashi Feng

Black-box attack methods aim to infer suitable attack patterns to targeted DNN models by only using output feedback of the models and the corresponding input queries.

Adversarial Attack Meta-Learning

Panoptic Edge Detection

no code implementations3 Jun 2019 Yuan Hu, Yingtian Zou, Jiashi Feng

In this work, we address a new finer-grained task, termed panoptic edge detection (PED), which aims at predicting semantic-level boundaries for stuff categories and instance-level boundaries for instance categories, in order to provide more comprehensive and unified scene understanding from the perspective of edges. We then propose a versatile framework, Panoptic Edge Network (PEN), which aggregates different tasks of object detection, semantic and instance edge detection into a single holistic network with multiple branches.

Edge Detection object-detection +2

Cross-Resolution Face Recognition via Prior-Aided Face Hallucination and Residual Knowledge Distillation

1 code implementation26 May 2019 Hanyang Kong, Jian Zhao, Xiaoguang Tu, Junliang Xing, ShengMei Shen, Jiashi Feng

Recent deep learning based face recognition methods have achieved great performance, but it still remains challenging to recognize very low-resolution query face like 28x28 pixels when CCTV camera is far from the captured subject.

Face Hallucination Face Recognition +2

Variational Prototype Replays for Continual Learning

1 code implementation23 May 2019 Mengmi Zhang, Tao Wang, Joo Hwee Lim, Gabriel Kreiman, Jiashi Feng

In each classification task, our method learns a set of variational prototypes with their means and variances, where embedding of the samples from the same class can be represented in a prototypical distribution and class-representative prototypes are separated apart.

Continual Learning General Classification +2

A Simple Pooling-Based Design for Real-Time Salient Object Detection

5 code implementations CVPR 2019 Jiang-Jiang Liu, Qibin Hou, Ming-Ming Cheng, Jiashi Feng, Jianmin Jiang

We further design a feature aggregation module (FAM) to make the coarse-level semantic information well fused with the fine-level features from the top-down pathway.

object-detection RGB Salient Object Detection +1

Hierarchical Meta Learning

no code implementations19 Apr 2019 Yingtian Zou, Jiashi Feng

Extensive experiments on few-shot classification and regression problems clearly demonstrate the superiority of HML over fine-tuning and state-of-the-art meta learning approaches in terms of generalization across heterogeneous tasks.

Few-Shot Learning

Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization

no code implementations17 Apr 2019 Li Yuan, Francis EH Tay, Ping Li, Li Zhou, Jiashi Feng

The evaluator defines a learnable information preserving metric between original video and summary video and "supervises" the selector to identify the most informative frames to form the summary video.

Unsupervised Video Summarization

Few-shot Adaptive Faster R-CNN

no code implementations CVPR 2019 Tao Wang, Xiaopeng Zhang, Li Yuan, Jiashi Feng

To address these challenges, we first introduce a pairing mechanism over source and target features to alleviate the issue of insufficient target domain samples.

object-detection Object Detection +1

Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search

2 code implementations CVPR 2019 Xin Li, Yiming Zhou, Zheng Pan, Jiashi Feng

It prunes the architecture search space with a partial order assumption to automatically search for the architectures with the best speed and accuracy trade-off.

Neural Architecture Search

Dynamic Feature Fusion for Semantic Edge Detection

1 code implementation25 Feb 2019 Yuan Hu, Yunpeng Chen, Xiang Li, Jiashi Feng

In this work, we propose a novel dynamic feature fusion strategy that assigns different fusion weights for different input images and locations adaptively.

Edge Detection

Multi-Prototype Networks for Unconstrained Set-based Face Recognition

no code implementations13 Feb 2019 Jian Zhao, Jianshu Li, Xiaoguang Tu, Fang Zhao, Yuan Xin, Junliang Xing, Hengzhu Liu, Shuicheng Yan, Jiashi Feng

In this paper, we study the challenging unconstrained set-based face recognition problem where each subject face is instantiated by a set of media (images and videos) instead of a single image.

Face Recognition

Deep Reasoning with Multi-Scale Context for Salient Object Detection

no code implementations24 Jan 2019 Zun Li, Congyan Lang, Yunpeng Chen, Junhao Liew, Jiashi Feng

However, the saliency inference module that performs saliency prediction from the fused features receives much less attention on its architecture design and typically adopts only a few fully convolutional layers.

object-detection RGB Salient Object Detection +2

Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing

1 code implementation17 Jan 2019 Xiaoguang Tu, Jian Zhao, Mei Xie, Guodong Du, Hengsheng Zhang, Jianshu Li, Zheng Ma, Jiashi Feng

Face anti-spoofing (a. k. a presentation attack detection) has drawn growing attention due to the high-security demand in face authentication systems.

Domain Adaptation Face Anti-Spoofing +1

Better Guider Predicts Future Better: Difference Guided Generative Adversarial Networks

no code implementations7 Jan 2019 Guohao Ying, Yingtian Zou, Lin Wan, Yiming Hu, Jiashi Feng

In this paper, we propose a novel GAN based on inter-frame difference to circumvent the difficulties.

Video Prediction

Similarity R-C3D for Few-shot Temporal Activity Detection

no code implementations25 Dec 2018 Huijuan Xu, Bingyi Kang, Ximeng Sun, Jiashi Feng, Kate Saenko, Trevor Darrell

In this paper, we present a conceptually simple and general yet novel framework for few-shot temporal activity detection which detects the start and end time of the few-shot input activities in an untrimmed video.

Action Detection Activity Detection

Few-shot Object Detection via Feature Reweighting

4 code implementations ICCV 2019 Bingyi Kang, Zhuang Liu, Xin Wang, Fisher Yu, Jiashi Feng, Trevor Darrell

The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples.

Few-Shot Learning Few-Shot Object Detection +2