AxWin Transformer: A Context-Aware Vision Transformer Backbone with Axial Windows

no code implementations • 2 May 2023 • Fangjian Lin, Yizhe Ma, Sitong Wu, Long Yu, Shengwei Tian

Recently Transformer has shown good performance in several vision tasks due to its powerful modeling capabilities.

Exploring vision transformer layer choosing for semantic segmentation

no code implementations • 2 May 2023 • Fangjian Lin, Yizhe Ma, Shengwei Tian

We validate the effectiveness of our method on different datasets and models and surpass previous state-of-the-art methods.

Decoder feature selection +1

PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation

no code implementations • 1 May 2023 • Yizhe Ma, Fangjian Lin, Sitong Wu, Shengwei Tian, Long Yu

We expect that our PRSeg can promote the development of MLP-based decoder in semantic segmentation.

Decoder Segmentation +1