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/DAT-T++

DAT-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 2017
AP· 2023-09-04
49.2
best: 53.4 (MaxViT-B)
DAT++: Spatially Dynamic Vision Transformer with Deformable Attention arXiv:2309.01430
2D ClassificationonCOCO 2017
AP· 2023-09-04
49.2
best: 53.4 (MaxViT-B)
DAT++: Spatially Dynamic Vision Transformer with Deformable Attention arXiv:2309.01430
2D Object DetectiononCOCO 2017
AP· 2023-09-04
49.2
best: 53.4 (MaxViT-B)
DAT++: Spatially Dynamic Vision Transformer with Deformable Attention arXiv:2309.01430
16konCOCO 2017
AP· 2023-09-04
49.2
best: 53.4 (MaxViT-B)
DAT++: Spatially Dynamic Vision Transformer with Deformable Attention arXiv:2309.01430

Computer Vision2 results

Object DetectiononCOCO 2017
AP· 2023-09-04
49.2
best: 53.4 (MaxViT-B)
DAT++: Spatially Dynamic Vision Transformer with Deformable Attention arXiv:2309.01430
Image ClassificationonImageNet
GFLOPs· 2023-09-04
4.3
best: 1478 (InternImage-H)
DAT++: Spatially Dynamic Vision Transformer with Deformable Attention arXiv:2309.01430

Medical1 result

Semantic SegmentationonADE20K
Validation mIoU· 2023-09-04
50.3
best: 63.6 (ViT-P (InternImage-H))
DAT++: Spatially Dynamic Vision Transformer with Deformable Attention arXiv:2309.01430

Audio1 result

10-shot image generationonADE20K
Validation mIoU· 2023-09-04
50.3
best: 63.6 (ViT-P (InternImage-H))
DAT++: Spatially Dynamic Vision Transformer with Deformable Attention arXiv:2309.01430