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/ELSA-S (Cascade Mask RCNN)

ELSA-S (Cascade Mask RCNN)

Reported on 18 benchmarks across 6 tasks · 1 paper

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

Methodology12 results

3DonCOCO minival
AP50· 2021-12-23
70.5
best: 82.1 (EVA)
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
3DonCOCO minival
AP75· 2021-12-23
56
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
3DonCOCO minival
box AP· 2021-12-23
51.6
best: 66 (PE_spatial (DETA))
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
2D ClassificationonCOCO minival
AP50· 2021-12-23
70.5
best: 82.1 (EVA)
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
2D ClassificationonCOCO minival
AP75· 2021-12-23
56
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
2D ClassificationonCOCO minival
box AP· 2021-12-23
51.6
best: 66 (PE_spatial (DETA))
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
2D Object DetectiononCOCO minival
AP50· 2021-12-23
70.5
best: 82.1 (EVA)
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
2D Object DetectiononCOCO minival
AP75· 2021-12-23
56
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
2D Object DetectiononCOCO minival
box AP· 2021-12-23
51.6
best: 66 (PE_spatial (DETA))
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
16konCOCO minival
AP50· 2021-12-23
70.5
best: 82.1 (EVA)
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
16konCOCO minival
AP75· 2021-12-23
56
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
16konCOCO minival
box AP· 2021-12-23
51.6
best: 66 (PE_spatial (DETA))
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786

Computer Vision6 results

Object DetectiononCOCO minival
AP50· 2021-12-23
70.5
best: 82.1 (EVA)
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
Object DetectiononCOCO minival
AP75· 2021-12-23
56
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
Object DetectiononCOCO minival
box AP· 2021-12-23
51.6
best: 66 (PE_spatial (DETA))
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
Instance SegmentationonCOCO minival
AP50· 2021-12-23
67.8
best: 80.1 (InternImage-H)
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
Instance SegmentationonCOCO minival
AP75· 2021-12-23
47.8
best: 62.8 (Co-DETR)
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786
Instance SegmentationonCOCO minival
mask AP· 2021-12-23
44.4
best: 56.6 (Co-DETR)
ELSA: Enhanced Local Self-Attention for Vision Transformer arXiv:2112.12786