240 citations
- Megvii (China)14 papers
- Peking UniversityCN4 papers
- Huazhong University of Science and TechnologyCN3 papers
- Institute of Computing TechnologyCN3 papers
- Tsinghua UniversityCN3 papers
- MEI Research (United States)US2 papers
- University of Electronic Science and Technology of ChinaCN2 papers
- Australian National UniversityAU1 paper
- Beijing Institute of TechnologyCN1 paper
- Beijing University of Posts and TelecommunicationsCN1 paper
- Carnegie Mellon UniversityUS1 paper
- Chinese Academy of SciencesCN1 paper
23 papers
Temporal Knowledge Consistency for Unsupervised Visual Representation Learning
Weixin Feng, Yuanjiang Wang, Lihua Ma +2
The instance discrimination paradigm has become dominant in unsupervised learning. It always adopts a teacher-student framework, in which the teacher provides embedded knowledge as…
GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning
Haipeng Li, Kunming Luo, Shuaicheng Liu
Existing optical flow methods are erroneous in challenging scenes, such as fog, rain, and night because the basic optical flow assumptions such as brightness and gradient constancy…
NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
Shen Cheng, Yuzhi Wang, Haibin Huang +3
In this paper, we introduce NBNet, a novel framework for image denoising. Unlike previous works, we propose to tackle this challenging problem from a new perspective: noise reducti…
Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection
Tiancai Wang, Tong Yang, Jiale Cao +1
Object detectors usually achieve promising results with the supervision of complete instance annotations. However, their performance is far from satisfactory with sparse instance a…
EqCo: Equivalent Rules for Self-supervised Contrastive Learning
Benjin Zhu, Junqiang Huang, Zeming Li +2
In this paper, we propose EqCo (Equivalent Rules for Contrastive Learning) to make self-supervised learning irrelevant to the number of negative samples in the contrastive learning…
WeightNet: Revisiting the Design Space of Weight Networks
Ningning Ma, Xiangyu Zhang, Jiawei Huang +1
We present a conceptually simple, flexible and effective framework for weight generating networks. Our approach is general that unifies two current distinct and extremely effective…