175 citations · 319 across the 22 of their papers we have counts for
5 papers · 1 filter
SwinIR: Image Restoration Using Swin Transformer
Jingyun Liang, Jiezhang Cao, Guolei Sun +3
Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). Whil…
Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
Jingyun Liang, Guolei Sun, Kai Zhang +2
Existing blind image super-resolution (SR) methods mostly assume blur kernels are spatially invariant across the whole image. However, such an assumption is rarely applicable for r…
Boosting Few-shot Semantic Segmentation with Transformers
Guolei Sun, Yun Liu, Jingyun Liang +1
Due to the fact that fully supervised semantic segmentation methods require sufficient fully-labeled data to work well and can not generalize to unseen classes, few-shot segmentati…
Vision Transformers with Hierarchical Attention
Yun Liu, Yu-Huan Wu, Guolei Sun +3
This paper tackles the high computational/space complexity associated with Multi-Head Self-Attention (MHSA) in vanilla vision transformers. To this end, we propose Hierarchical MHS…
Rethinking Global Context in Crowd Counting
Guolei Sun, Yun Liu, Thomas Probst +3
This paper investigates the role of global context for crowd counting. Specifically, a pure transformer is used to extract features with global information from overlapping image p…