619 citations · 6.4k across the 178 of their papers we have counts for
27 papers · 1 filter
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
Jian Liang, Dapeng Hu, Yunbo Wang +2
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods…
Improving Generalization in Reinforcement Learning with Mixture Regularization
Kaixin Wang, Bingyi Kang, Jie Shao +1
Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments. To improve their…
Towards Accurate Human Pose Estimation in Videos of Crowded Scenes
Li Yuan, Shuning Chang, Xuecheng Nie +5
Video-based human pose estimation in crowded scenes is a challenging problem due to occlusion, motion blur, scale variation and viewpoint change, etc. Prior approaches always fail…
A Simple Baseline for Pose Tracking in Videos of Crowded Scenes
Li Yuan, Shuning Chang, Ziyuan Huang +6
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 Po…
Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes
Li Yuan, Yichen Zhou, Shuning Chang +6
Detecting and recognizing human action in videos with crowded scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal w…
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning
Pan Zhou, Jiashi Feng, Chao Ma +3
It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide…
Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations
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. Inspired by human rea…
Dual Adversarial Auto-Encoders for Clustering
Pengfei Ge, Chuan-Xian Ren, Jiashi Feng +1
As a powerful approach for exploratory data analysis, unsupervised clustering is a fundamental task in computer vision and pattern recognition. Many clustering algorithms have been…
ConvBERT: Improving BERT with Span-based Dynamic Convolution
Zihang Jiang, Weihao Yu, Daquan Zhou +3
Pre-trained language models like BERT and its variants have recently achieved impressive performance in various natural language understanding tasks. However, BERT heavily relies o…
Few-shot Classification via Adaptive Attention
Zihang Jiang, Bingyi Kang, Kuangqi Zhou +1
Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly con…
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition
Chenyang Si, Xuecheng Nie, Wei Wang +3
We consider the problem of semi-supervised 3D action recognition which has been rarely explored before. Its major challenge lies in how to effectively learn motion representations…
Local Grid Rendering Networks for 3D Object Detection in Point Clouds
Jianan Li, Jiashi Feng
The performance of 3D object detection models over point clouds highly depends on their capability of modeling local geometric patterns. Conventional point-based models exploit loc…
Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation
Jianfeng Zhang, Xuecheng Nie, Jiashi Feng
Existing 3D human pose estimation models suffer performance drop when applying to new scenarios with unseen poses due to their limited generalizability. In this work, we propose a…
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
Tao Wang, Yu Li, Bingyi Kang +5
Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO…
Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
Jian Liang, Dapeng Hu, Jiashi Feng
Domain adaptation (DA) aims to transfer knowledge from a label-rich but heterogeneous domain to a label-scare domain, which alleviates the labeling efforts and attracts considerabl…
Rethinking Bottleneck Structure for Efficient Mobile Network Design
Zhou Daquan, Qibin Hou, Yunpeng Chen +2
The inverted residual block is dominating architecture design for mobile networks recently. It changes the classic residual bottleneck by introducing two design rules: learning inv…
Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
Yu Li, Tao Wang, Bingyi Kang +4
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 th…
Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation
Kuangqi Zhou, Qibin Hou, Zun Li +1
Object region mining is a critical step for weakly-supervised semantic segmentation. Most recent methods mine the object regions by expanding the seed regions localized by class ac…
Boosting Few-Shot Learning With Adaptive Margin Loss
Aoxue Li, Weiran Huang, Xu Lan +3
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. T…
RAIN: A Simple Approach for Robust and Accurate Image Classification Networks
Jiawei Du, Hanshu Yan, Vincent Y. F. Tan +3
It has been shown that the majority of existing adversarial defense methods achieve robustness at the cost of sacrificing prediction accuracy. The undesirable severe drop in accura…
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
Qibin Hou, Li Zhang, Ming-Ming Cheng +1
Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing. In this paper, beyond conven…
A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
Jian Liang, Yunbo Wang, Dapeng Hu +2
This work addresses the unsupervised domain adaptation problem, especially in the case of class labels in the target domain being only a subset of those in the source domain. Such…
Cross-layer Feature Pyramid Network for Salient Object Detection
Zun Li, Congyan Lang, Junhao Liew +3
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. How…
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
Jian Liang, Dapeng Hu, Jiashi Feng
Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typica…