Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:SGIGU2WLrecord.jsonopen to challenge →
read the original abstract
Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been devoted to the cross-window connection which is the key element to improve the representation ability. In this work, we revisit the spatial shuffle as an efficient way to build connections among windows. As a result, we propose a new vision transformer, named Shuffle Transformer, which is highly efficient and easy to implement by modifying two lines of code. Furthermore, the depth-wise convolution is introduced to complement the spatial shuffle for enhancing neighbor-window connections. The proposed architectures achieve excellent performance on a wide range of visual tasks including image-level classification, object detection, and semantic segmentation. Code will be released for reproduction.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer
The OG-ReG Transformer achieves state-of-the-art results on Kinetics-400, Something-Something v2, and Diving-48 by combining global glance and local gaze processing paths.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.