Pith. sign in

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

arxiv 2106.03650 v1 pith:SGIGU2WL submitted 2021-06-07 cs.CV

classification cs.CV
keywords shuffletransformerspatialclassificationcodeconnectionsdetectionefficient
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding

    cs.CV 2025-01 conditional novelty 5.0 of 10

    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...

  2. Hierarchical Information Flow for Generalized Efficient Image Restoration

    cs.CV 2024-11 conditional novelty 5.0 of 10

    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.

Pith tools