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/Focal-L (DyHead, multi-scale)

Focal-L (DyHead, multi-scale)

Reported on 20 benchmarks across 5 tasks · 1 paper

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

Methodology16 results

3DonCOCO test-dev
box mAP· 2021-07-01
58.9
best: 66 (Co-DETR)
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
3DonCOCO minival
AP50· 2021-07-01
77.2
best: 82.1 (EVA)
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
3DonCOCO minival
APL· 2021-07-01
73.4
best: 78.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
3DonCOCO minival
box AP· 2021-07-01
58.7
best: 66 (PE_spatial (DETA))
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
2D ClassificationonCOCO test-dev
box mAP· 2021-07-01
58.9
best: 66 (Co-DETR)
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
2D ClassificationonCOCO minival
AP50· 2021-07-01
77.2
best: 82.1 (EVA)
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
2D ClassificationonCOCO minival
APL· 2021-07-01
73.4
best: 78.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
2D ClassificationonCOCO minival
box AP· 2021-07-01
58.7
best: 66 (PE_spatial (DETA))
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
2D Object DetectiononCOCO test-dev
box mAP· 2021-07-01
58.9
best: 66 (Co-DETR)
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
2D Object DetectiononCOCO minival
AP50· 2021-07-01
77.2
best: 82.1 (EVA)
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
2D Object DetectiononCOCO minival
APL· 2021-07-01
73.4
best: 78.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
2D Object DetectiononCOCO minival
box AP· 2021-07-01
58.7
best: 66 (PE_spatial (DETA))
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
16konCOCO test-dev
box mAP· 2021-07-01
58.9
best: 66 (Co-DETR)
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
16konCOCO minival
AP50· 2021-07-01
77.2
best: 82.1 (EVA)
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
16konCOCO minival
APL· 2021-07-01
73.4
best: 78.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
16konCOCO minival
box AP· 2021-07-01
58.7
best: 66 (PE_spatial (DETA))
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641

Computer Vision4 results

Object DetectiononCOCO test-dev
box mAP· 2021-07-01
58.9
best: 66 (Co-DETR)
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
Object DetectiononCOCO minival
AP50· 2021-07-01
77.2
best: 82.1 (EVA)
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
Object DetectiononCOCO minival
APL· 2021-07-01
73.4
best: 78.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641
Object DetectiononCOCO minival
box AP· 2021-07-01
58.7
best: 66 (PE_spatial (DETA))
Focal Self-attention for Local-Global Interactions in Vision Transformers arXiv:2107.00641