32 citations · 76 across the 7 of their papers we have counts for
7 papers
AxWin Transformer: A Context-Aware Vision Transformer Backbone with Axial Windows
Fangjian Lin, Yizhe Ma, Sitong Wu +2
Recently Transformer has shown good performance in several vision tasks due to its powerful modeling capabilities. To reduce the quadratic complexity caused by the attention, some…
Exploring vision transformer layer choosing for semantic segmentation
Fangjian Lin, Yizhe Ma, Shengwei Tian
Extensive work has demonstrated the effectiveness of Vision Transformers. The plain Vision Transformer tends to obtain multi-scale features by selecting fixed layers, or the last l…
PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation
Yizhe Ma, Fangjian Lin, Sitong Wu +2
The lightweight MLP-based decoder has become increasingly promising for semantic segmentation. However, the channel-wise MLP cannot expand the receptive fields, lacking the context…
UniNeXt: Exploring A Unified Architecture for Vision Recognition
Fangjian Lin, Jianlong Yuan, Sitong Wu +2
Vision Transformers have shown great potential in computer vision tasks. Most recent works have focused on elaborating the spatial token mixer for performance gains. However, we ob…
Feature Selective Transformer for Semantic Image Segmentation
Fangjian Lin, Tianyi Wu, Sitong Wu +2
Recently, it has attracted more and more attentions to fuse multi-scale features for semantic image segmentation. Various works were proposed to employ progressive local or global…
StructToken : Rethinking Semantic Segmentation with Structural Prior
Fangjian Lin, Zhanhao Liang, Sitong Wu +3
In previous deep-learning-based methods, semantic segmentation has been regarded as a static or dynamic per-pixel classification task, \textit{i.e.,} classify each pixel representa…
Fully Transformer Networks for Semantic Image Segmentation
Sitong Wu, Tianyi Wu, Fangjian Lin +2
Transformers have shown impressive performance in various natural language processing and computer vision tasks, due to the capability of modeling long-range dependencies. Recent p…