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/RetinaNet+aLRP Loss (ResNet-50, 500 scale)

RetinaNet+aLRP Loss (ResNet-50, 500 scale)

Reported on 15 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.

Methodology12 results

3DonCOCO minival
AP50· 2020-09-28
60.3
best: 82.1 (EVA)
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
3DonCOCO minival
AP75· 2020-09-28
42.3
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
3DonCOCO minival
box AP· 2020-09-28
40.2
best: 66 (PE_spatial (DETA))
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
2D ClassificationonCOCO minival
AP50· 2020-09-28
60.3
best: 82.1 (EVA)
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
2D ClassificationonCOCO minival
AP75· 2020-09-28
42.3
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
2D ClassificationonCOCO minival
box AP· 2020-09-28
40.2
best: 66 (PE_spatial (DETA))
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
2D Object DetectiononCOCO minival
AP50· 2020-09-28
60.3
best: 82.1 (EVA)
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
2D Object DetectiononCOCO minival
AP75· 2020-09-28
42.3
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
2D Object DetectiononCOCO minival
box AP· 2020-09-28
40.2
best: 66 (PE_spatial (DETA))
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
16konCOCO minival
AP50· 2020-09-28
60.3
best: 82.1 (EVA)
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
16konCOCO minival
AP75· 2020-09-28
42.3
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
16konCOCO minival
box AP· 2020-09-28
40.2
best: 66 (PE_spatial (DETA))
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592

Computer Vision3 results

Object DetectiononCOCO minival
AP50· 2020-09-28
60.3
best: 82.1 (EVA)
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
Object DetectiononCOCO minival
AP75· 2020-09-28
42.3
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592
Object DetectiononCOCO minival
box AP· 2020-09-28
40.2
best: 66 (PE_spatial (DETA))
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection arXiv:2009.13592