42 citations · 214 across the 65 of their papers we have counts for
13 papers · 1 filter
Activating the Discriminability of Novel Classes for Few-shot Segmentation
Dianwen Mei, Wei Zhuo, Jiandong Tian +2
Despite the remarkable success of existing methods for few-shot segmentation, there remain two crucial challenges. First, the feature learning for novel classes is suppressed durin…
Semantic-Aware Local-Global Vision Transformer
Jiatong Zhang, Zengwei Yao, Fanglin Chen +2
Vision Transformers have achieved remarkable progresses, among which Swin Transformer has demonstrated the tremendous potential of Transformer for vision tasks. It surmounts the ke…
Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid
Jing Xu, Xu Luo, Xinglin Pan +3
Few-shot learning (FSL) targets at generalization of vision models towards unseen tasks without sufficient annotations. Despite the emergence of a number of few-shot learning metho…
SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation
Yi Li, Wenjie Pei, Zhenyu He
The traditional homography estimation pipeline consists of four main steps: feature detection, feature matching, outlier removal and transformation estimation. Recent deep learning…
Layout-Bridging Text-to-Image Synthesis
Jiadong Liang, Wenjie Pei, Feng Lu
The crux of text-to-image synthesis stems from the difficulty of preserving the cross-modality semantic consistency between the input text and the synthesized image. Typical method…
Learning Generalizable Latent Representations for Novel Degradations in Super Resolution
Fengjun Li, Xin Feng, Fanglin Chen +2
Typical methods for blind image super-resolution (SR) focus on dealing with unknown degradations by directly estimating them or learning the degradation representations in a latent…
Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations
Wenjie Pei, Shuang Wu, Dianwen Mei +3
While fine-tuning based methods for few-shot object detection have achieved remarkable progress, a crucial challenge that has not been addressed well is the potential class-specifi…
Self-Support Few-Shot Semantic Segmentation
Qi Fan, Wenjie Pei, Yu-Wing Tai +1
Existing few-shot segmentation methods have achieved great progress based on the support-query matching framework. But they still heavily suffer from the limited coverage of intra-…
Learning Sequence Representations by Non-local Recurrent Neural Memory
Wenjie Pei, Xin Feng, Canmiao Fu +3
The key challenge of sequence representation learning is to capture the long-range temporal dependencies. Typical methods for supervised sequence representation learning are built…
Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection
Shuang Wu, Wenjie Pei, Dianwen Mei +3
Most of existing methods for few-shot object detection follow the fine-tuning paradigm, which potentially assumes that the class-agnostic generalizable knowledge can be learned and…
Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration
Xin Feng, Haobo Ji, Wenjie Pei +2
While the research on image background restoration from regular size of degraded images has achieved remarkable progress, restoring ultra high-resolution (e.g., 4K) images remains…
Single Shot Self-Reliant Scene Text Spotter by Decoupled yet Collaborative Detection and Recognition
Jingjing Wu, Pengyuan Lyu, Guangming Lu +2
Typical text spotters follow the two-stage spotting paradigm which detects the boundary for a text instance first and then performs text recognition within the detected regions. De…
Global Tracking via Ensemble of Local Trackers
Zikun Zhou, Jianqiu Chen, Wenjie Pei +3
The crux of long-term tracking lies in the difficulty of tracking the target with discontinuous moving caused by out-of-view or occlusion. Existing long-term tracking methods follo…