1.6k citations · 6.8k across the 186 of their papers we have counts for
11 papers · 1 filter
Diversity Transfer Network for Few-Shot Learning
Mengting Chen, Yuxin Fang, Xinggang Wang +6
Few-shot learning is a challenging task that aims at training a classifier for unseen classes with only a few training examples. The main difficulty of few-shot learning lies in th…
IoU-aware Single-stage Object Detector for Accurate Localization
Shengkai Wu, Xiaoping Li, Xinggang Wang
Due to the simpleness and high efficiency, single-stage object detectors have been widely applied in many computer vision applications . However, the low correlation between the cl…
Deep High-Resolution Representation Learning for Visual Recognition
Jingdong Wang, Ke Sun, Tianheng Cheng +9
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-…
Object Detection in Video with Spatial-temporal Context Aggregation
Hao Luo, Lichao Huang, Han Shen +3
Recent cutting-edge feature aggregation paradigms for video object detection rely on inferring feature correspondence. The feature correspondence estimation problem is fundamentall…
Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
Qiang Zhou, Zilong Huang, Lichao Huang +5
Video object segmentation (VOS) aims at pixel-level object tracking given only the annotations in the first frame. Due to the large visual variations of objects in video and the la…
Densely Connected Search Space for More Flexible Neural Architecture Search
Jiemin Fang, Yuzhu Sun, Qian Zhang +3
Neural architecture search (NAS) has dramatically advanced the development of neural network design. We revisit the search space design in most previous NAS methods and find the nu…
Reducing the dilution: An analysis of the information sensitiveness of capsule network with a practical improvement method
Zonglin Yang, Xinggang Wang
Capsule network has shown various advantages over convolutional neural network (CNN). It keeps more precise spatial information than CNN and uses equivariance instead of invariance…
High-Resolution Representations for Labeling Pixels and Regions
Ke Sun, Yang Zhao, Borui Jiang +7
High-resolution representation learning plays an essential role in many vision problems, e.g., pose estimation and semantic segmentation. The high-resolution network (HRNet)~\cite{…
Direct Object Recognition Without Line-of-Sight Using Optical Coherence
Xin Lei, Liangyu He, Yixuan Tan +5
Visual object recognition under situations in which the direct line-of-sight is blocked, such as when it is occluded around the corner, is of practical importance in a wide range o…
Mask Scoring R-CNN
Zhaojin Huang, Lichao Huang, Yongchao Gong +2
Letting a deep network be aware of the quality of its own predictions is an interesting yet important problem. In the task of instance segmentation, the confidence of instance clas…
EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
Jiemin Fang, Yukang Chen, Xinbang Zhang +5
Neural architecture search (NAS) methods have been proposed to release human experts from tedious architecture engineering. However, most current methods are constrained in small-s…