Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Shift-T

Shift-T

Reported on 8 benchmarks across 8 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

3DonCOCO minival
APM· 2022-01-26
42.3
best: 68.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism arXiv:2201.10801
2D ClassificationonCOCO minival
APM· 2022-01-26
42.3
best: 68.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism arXiv:2201.10801
2D Object DetectiononCOCO minival
APM· 2022-01-26
42.3
best: 68.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism arXiv:2201.10801
16konCOCO minival
APM· 2022-01-26
42.3
best: 68.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism arXiv:2201.10801

Computer Vision2 results

Object DetectiononCOCO minival
APM· 2022-01-26
42.3
best: 68.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism arXiv:2201.10801
Image ClassificationonImageNet
GFLOPs· 2022-01-26
4.4
best: 1478 (InternImage-H)
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism arXiv:2201.10801

Medical1 result

Semantic SegmentationonADE20K
Validation mIoU· 2022-01-26
46.3
best: 63.6 (ViT-P (InternImage-H))
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism arXiv:2201.10801

Audio1 result

10-shot image generationonADE20K
Validation mIoU· 2022-01-26
46.3
best: 63.6 (ViT-P (InternImage-H))
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism arXiv:2201.10801