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/dBOT ViT-B (CLIP)

dBOT ViT-B (CLIP)

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 test-dev
box mAP· 2022-09-08
53.6
best: 66 (Co-DETR)
Exploring Target Representations for Masked Autoencoders arXiv:2209.03917
2D ClassificationonCOCO test-dev
box mAP· 2022-09-08
53.6
best: 66 (Co-DETR)
Exploring Target Representations for Masked Autoencoders arXiv:2209.03917
2D Object DetectiononCOCO test-dev
box mAP· 2022-09-08
53.6
best: 66 (Co-DETR)
Exploring Target Representations for Masked Autoencoders arXiv:2209.03917
16konCOCO test-dev
box mAP· 2022-09-08
53.6
best: 66 (Co-DETR)
Exploring Target Representations for Masked Autoencoders arXiv:2209.03917

Computer Vision2 results

Object DetectiononCOCO test-dev
box mAP· 2022-09-08
53.6
best: 66 (Co-DETR)
Exploring Target Representations for Masked Autoencoders arXiv:2209.03917
Instance SegmentationonCOCO test-dev
mask AP· 2022-09-08
46.2
best: 57.1 (Co-DETR)
Exploring Target Representations for Masked Autoencoders arXiv:2209.03917

Medical1 result

Semantic SegmentationonADE20K
Validation mIoU· 2022-09-08
52.9
best: 63.6 (ViT-P (InternImage-H))
Exploring Target Representations for Masked Autoencoders arXiv:2209.03917

Audio1 result

10-shot image generationonADE20K
Validation mIoU· 2022-09-08
52.9
best: 63.6 (ViT-P (InternImage-H))
Exploring Target Representations for Masked Autoencoders arXiv:2209.03917