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/ISTR (ResNet101-FPN-3x, single-scale)

ISTR (ResNet101-FPN-3x, single-scale)

Reported on 23 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.

Methodology16 results

3DonCOCO test-dev
APL· 2021-05-03
61.5
best: 86.5 (PoseBH-H)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
3DonCOCO test-dev
APM· 2021-05-03
50.4
best: 83.8 (4xRSN-50 (ensemble))
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
3DonCOCO test-dev
APS· 2021-05-03
28.7
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
3DonCOCO test-dev
box mAP· 2021-05-03
48.1
best: 66 (Co-DETR)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
2D ClassificationonCOCO test-dev
APL· 2021-05-03
61.5
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
2D ClassificationonCOCO test-dev
APM· 2021-05-03
50.4
best: 67.7 (EVA)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
2D ClassificationonCOCO test-dev
APS· 2021-05-03
28.7
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
2D ClassificationonCOCO test-dev
box mAP· 2021-05-03
48.1
best: 66 (Co-DETR)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
2D Object DetectiononCOCO test-dev
APL· 2021-05-03
61.5
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
2D Object DetectiononCOCO test-dev
APM· 2021-05-03
50.4
best: 67.7 (EVA)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
2D Object DetectiononCOCO test-dev
APS· 2021-05-03
28.7
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
2D Object DetectiononCOCO test-dev
box mAP· 2021-05-03
48.1
best: 66 (Co-DETR)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
16konCOCO test-dev
APL· 2021-05-03
61.5
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
16konCOCO test-dev
APM· 2021-05-03
50.4
best: 67.7 (EVA)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
16konCOCO test-dev
APS· 2021-05-03
28.7
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
16konCOCO test-dev
box mAP· 2021-05-03
48.1
best: 66 (Co-DETR)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637

Computer Vision7 results

Object DetectiononCOCO test-dev
APL· 2021-05-03
61.5
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
Object DetectiononCOCO test-dev
APM· 2021-05-03
50.4
best: 67.7 (EVA)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
Object DetectiononCOCO test-dev
APS· 2021-05-03
28.7
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
Object DetectiononCOCO test-dev
box mAP· 2021-05-03
48.1
best: 66 (Co-DETR)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
Instance SegmentationonCOCO test-dev
APL· 2021-05-03
52.3
best: 72.4 (EVA)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
Instance SegmentationonCOCO test-dev
APM· 2021-05-03
41.9
best: 60.1 (Co-DETR)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637
Instance SegmentationonCOCO test-dev
APS· 2021-05-03
22.8
best: 41.6 (Co-DETR)
ISTR: End-to-End Instance Segmentation with Transformers arXiv:2105.00637