Jiashi Feng

is this you? claim profile

∙ 2 followers
National University of Singapore ∙ berkeley college

Assistant Professor at National University of Singapore

Test-Agnostic Long-Tailed Recognition by Test-Time Aggregating Diverse Experts with Self-Supervision

Existing long-tailed recognition methods, aiming to train class-balance ...
07/20/2021 ∙ by Yifan Zhang, et al. ∙ 1 ∙ share

read it
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing

The Laplacian representation recently gains increasing attention for rei...
07/12/2021 ∙ by Kaixin Wang, et al. ∙ 26 ∙ share

read it
Recovering the Unbiased Scene Graphs from the Biased Ones

Given input images, scene graph generation (SGG) aims to produce compreh...
07/05/2021 ∙ by Meng-Jiun Chiou, et al. ∙ 9 ∙ share

read it
VOLO: Vision Outlooker for Visual Recognition

Visual recognition has been dominated by convolutional neural networks (...
06/24/2021 ∙ by Li Yuan, et al. ∙ 0 ∙ share

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

In this paper, we present Vision Permutator, a conceptually simple and d...
06/23/2021 ∙ by Qibin Hou, et al. ∙ 0 ∙ share

read it
LV-BERT: Exploiting Layer Variety for BERT

Modern pre-trained language models are mostly built upon backbones stack...
06/22/2021 ∙ by Weihao Yu, et al. ∙ 12 ∙ share

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

A central challenge in training classification models in the real-world ...
06/09/2021 ∙ by Mi Luo, et al. ∙ 9 ∙ share

read it
Image-to-Video Generation via 3D Facial Dynamics

We present a versatile model, FaceAnime, for various video generation ta...
05/31/2021 ∙ by Xiaoguang Tu, et al. ∙ 17 ∙ share

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

In this paper, we address the makeup transfer and removal tasks simultan...
05/26/2021 ∙ by Si Liu, et al. ∙ 7 ∙ share

read it
ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos

Detecting human-object interactions (HOI) is an important step toward a ...
05/25/2021 ∙ by Meng-Jiun Chiou, et al. ∙ 6 ∙ share

read it
Continual Learning via Bit-Level Information Preserving

Continual learning tackles the setting of learning different tasks seque...
05/10/2021 ∙ by Yujun Shi, et al. ∙ 0 ∙ share

read it
Body Meshes as Points

We consider the challenging multi-person 3D body mesh estimation task in...
05/06/2021 ∙ by Jianfeng Zhang, et al. ∙ 0 ∙ share

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

Existing 3D human pose estimators suffer poor generalization performance...
05/06/2021 ∙ by Kehong Gong, et al. ∙ 0 ∙ share

read it
How Well Self-Supervised Pre-Training Performs with Streaming Data?

The common self-supervised pre-training practice requires collecting mas...
04/25/2021 ∙ by Dapeng Hu, et al. ∙ 11 ∙ share

read it
Token Labeling: Training a 85.4 56M Parameters on ImageNet

This paper provides a strong baseline for vision transformers on the Ima...
04/22/2021 ∙ by Zihang Jiang, et al. ∙ 0 ∙ share

read it
Distill and Fine-tune: Effective Adaptation from a Black-box Source Model

To alleviate the burden of labeling, unsupervised domain adaptation (UDA...
04/04/2021 ∙ by Jian Liang, et al. ∙ 0 ∙ share

read it
Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation

Temporal action proposal generation (TAPG) is a fundamental and challeng...
03/30/2021 ∙ by Shuning Chang, et al. ∙ 9 ∙ share

read it
DeepViT: Towards Deeper Vision Transformer

Vision transformers (ViTs) have been successfully applied in image class...
03/22/2021 ∙ by Daquan Zhou, et al. ∙ 0 ∙ share

read it
AutoSpace: Neural Architecture Search with Less Human Interference

Current neural architecture search (NAS) algorithms still require expert...
03/22/2021 ∙ by Daquan Zhou, et al. ∙ 0 ∙ share

read it
Coordinate Attention for Efficient Mobile Network Design

Recent studies on mobile network design have demonstrated the remarkable...
03/04/2021 ∙ by Qibin Hou, et al. ∙ 0 ∙ share

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

Contrastive self-supervised learning (CSL) leverages unlabeled data to t...
02/12/2021 ∙ by Yifan Zhang, et al. ∙ 0 ∙ share

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

We investigate the adversarial robustness of CNNs from the perspective o...
02/10/2021 ∙ by Hanshu Yan, et al. ∙ 0 ∙ share

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

Transformers, which are popular for language modeling, have been explore...
01/28/2021 ∙ by Li Yuan, et al. ∙ 34 ∙ share

read it
ORDNet: Capturing Omni-Range Dependencies for Scene Parsing

Learning to capture dependencies between spatial positions is essential ...
01/11/2021 ∙ by Shaofei Huang, et al. ∙ 8 ∙ share

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

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a r...
12/14/2020 ∙ by Jian Liang, et al. ∙ 0 ∙ share

read it
Adversarial images for the primate brain

Deep artificial neural networks have been proposed as a model of primate...
11/11/2020 ∙ by Li Yuan, et al. ∙ 1 ∙ share

read it
Improving Generalization in Reinforcement Learning with Mixture Regularization

Deep reinforcement learning (RL) agents trained in a limited set of envi...
10/21/2020 ∙ by Kaixin Wang, et al. ∙ 0 ∙ share

read it
Towards Accurate Human Pose Estimation in Videos of Crowded Scenes

Video-based human pose estimation in crowded scenes is a challenging pro...
10/16/2020 ∙ by Li Yuan, et al. ∙ 1 ∙ share

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

Detecting and recognizing human action in videos with crowded scenes is ...
10/16/2020 ∙ by Li Yuan, et al. ∙ 1 ∙ share

read it
A Simple Baseline for Pose Tracking in Videos of Crowded Scenes

This paper presents our solution to ACM MM challenge: Large-scale Human-...
10/16/2020 ∙ by Li Yuan, et al. ∙ 1 ∙ share

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

It is not clear yet why ADAM-alike adaptive gradient algorithms suffer f...
10/12/2020 ∙ by Pan Zhou, et al. ∙ 46 ∙ share

read it
RVL-BERT: Visual Relationship Detection with Visual-Linguistic Knowledge from Pre-trained Representations

Visual relationship detection aims to reason over relationships among sa...
09/10/2020 ∙ by Meng-Jiun Chiou, et al. ∙ 16 ∙ share

read it
Dual Adversarial Auto-Encoders for Clustering

As a powerful approach for exploratory data analysis, unsupervised clust...
08/23/2020 ∙ by Pengfei Ge, et al. ∙ 0 ∙ share

read it
ConvBERT: Improving BERT with Span-based Dynamic Convolution

Pre-trained language models like BERT and its variants have recently ach...
08/06/2020 ∙ by Zihang Jiang, et al. ∙ 0 ∙ share

read it
Few-shot Classification via Adaptive Attention

Training a neural network model that can quickly adapt to a new task is ...
08/06/2020 ∙ by Zihang Jiang, et al. ∙ 0 ∙ share

read it
The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

Most existing object instance detection and segmentation models only wor...
07/23/2020 ∙ by Tao Wang, et al. ∙ 0 ∙ share

read it
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition

We consider the problem of semi-supervised 3D action recognition which h...
07/12/2020 ∙ by Chenyang Si, et al. ∙ 12 ∙ share

read it
Combating Domain Shift with Self-Taught Labeling

We present a novel method to combat domain shift when adapting classific...
07/08/2020 ∙ by Jian Liang, et al. ∙ 0 ∙ share

read it
Rethinking Bottleneck Structure for Efficient Mobile Network Design

The inverted residual block is dominating architecture design for mobile...
07/05/2020 ∙ by Zhou Daquan, et al. ∙ 0 ∙ share

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

The performance of 3D object detection models over point clouds highly d...
07/04/2020 ∙ by Jianan Li, et al. ∙ 0 ∙ share

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

Existing 3D human pose estimation models suffer performance drop when ap...
07/04/2020 ∙ by Jianfeng Zhang, et al. ∙ 0 ∙ share

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

Solving long-tail large vocabulary object detection with deep learning b...
06/18/2020 ∙ by Yu Li, et al. ∙ 12 ∙ share

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

Object region mining is a critical step for weakly-supervised semantic s...
06/14/2020 ∙ by Kuangqi Zhou, et al. ∙ 0 ∙ share

read it
Effective Training Strategies for Deep Graph Neural Networks

Graph Neural Networks (GNNs) tend to suffer performance degradation as m...
06/12/2020 ∙ by Kuangqi Zhou, et al. ∙ 0 ∙ share

read it
Boosting Few-Shot Learning With Adaptive Margin Loss

Few-shot learning (FSL) has attracted increasing attention in recent yea...
05/28/2020 ∙ by Aoxue Li, et al. ∙ 5 ∙ share

read it
RAIN: Robust and Accurate Classification Networks with Randomization and Enhancement

Along with the extensive applications of CNN models for classification, ...
04/24/2020 ∙ by Jiawei Du, et al. ∙ 0 ∙ share

read it
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

Spatial pooling has been proven highly effective in capturing long-range...
03/30/2020 ∙ by Qibin Hou, et al. ∙ 7 ∙ share

read it
PANDA: Prototypical Unsupervised Domain Adaptation

Previous adversarial domain alignment methods for unsupervised domain ad...
03/30/2020 ∙ by Dapeng Hu, et al. ∙ 0 ∙ share

read it
A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation

This work addresses the unsupervised domain adaptation problem, especial...
03/05/2020 ∙ by Jian Liang, et al. ∙ 0 ∙ share

read it
Cross-layer Feature Pyramid Network for Salient Object Detection

Feature pyramid network (FPN) based models, which fuse the semantics and...
02/25/2020 ∙ by Zun Li, et al. ∙ 0 ∙ share

read it

Jiashi Feng

Featured Co-authors