1.6k citations
- Vi Technology (United States)US14 papers
- Tsinghua UniversityCN12 papers
- Peking UniversityCN10 papers
- University of Electronic Science and Technology of ChinaCN10 papers
- Chinese Academy of SciencesCN9 papers
- Huazhong University of Science and TechnologyCN8 papers
- Hong Kong University of Science and TechnologyHK7 papers
- Tongji UniversityCN5 papers
- University of Science and Technology of ChinaCN5 papers
- Chinese University of Hong KongHK4 papers
- Institute of AutomationCN4 papers
- Tencent (China)CN4 papers
83 papers
Class Balance Matters to Active Class-Incremental Learning
Zitong Huang, Ze Chen, Yuanze Li +6
Few-Shot Class-Incremental Learning has shown remarkable efficacy in efficient learning new concepts with limited annotations. Nevertheless, the heuristic few-shot annotations may…
PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training
Suyi Chen, Hao Xu, Haipeng Li +5
Data plays a crucial role in training learning-based methods for 3D point cloud registration. However, the real-world dataset is expensive to build, while rendering-based synthetic…
Label-guided Attention Distillation for Lane Segmentation
Zhikang Liu, Lanyun Zhu
Contemporary segmentation methods are usually based on deep fully convolutional networks (FCNs). However, the layer-by-layer convolutions with a growing receptive field is not good…
Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling
Hansen Feng, Lizhi Wang, Yuzhi Wang +1
Low-light raw denoising is an important and valuable task in computational photography where learning-based methods trained with paired real data are mainstream. However, the limit…
SiamPolar: Semi-supervised Realtime Video Object Segmentation with Polar Representation
Yaochen Li, Yuhui Hong, Yonghong Song +3
Video object segmentation (VOS) is an essential part of autonomous vehicle navigation. The real-time speed is very important for the autonomous vehicle algorithms along with the ac…
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…