REVIEW 2 cited by
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
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.
Forward citations
Cited by 2 Pith papers
-
Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding
PIIP is a multi-branch, parameter-inverted image pyramid that uses smaller pretrained networks for high-resolution inputs and larger networks for low-resolution inputs, improving efficiency across perception and multi...
-
Hierarchical Information Flow for Generalized Efficient Image Restoration
Hi-IR is a hierarchical three-level attention network that achieves top results on several image restoration benchmarks while using fewer parameters than prior transformer methods.
Discussion (0). Continue with ORCID to comment.