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/Libra R-CNN (ResNeXt-101-FPN)

Libra R-CNN (ResNeXt-101-FPN)

Reported on 30 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.

Methodology24 results

3DonCOCO test-dev
AP50· 2019-04-04
64
best: 95 (ViTPose (ViTAE-G, ensemble))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
3DonCOCO test-dev
AP75· 2019-04-04
47
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
3DonCOCO test-dev
APL· 2019-04-04
54.6
best: 86.5 (PoseBH-H)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
3DonCOCO test-dev
APM· 2019-04-04
45.6
best: 83.8 (4xRSN-50 (ensemble))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
3DonCOCO test-dev
APS· 2019-04-04
25.3
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
3DonCOCO test-dev
box mAP· 2019-04-04
43
best: 66 (Co-DETR)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D ClassificationonCOCO test-dev
AP50· 2019-04-04
64
best: 82.1 (Plain-DETR (Swin-L))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D ClassificationonCOCO test-dev
AP75· 2019-04-04
47
best: 71.7 (EVA)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D ClassificationonCOCO test-dev
APL· 2019-04-04
54.6
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D ClassificationonCOCO test-dev
APM· 2019-04-04
45.6
best: 67.7 (EVA)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D ClassificationonCOCO test-dev
APS· 2019-04-04
25.3
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D ClassificationonCOCO test-dev
box mAP· 2019-04-04
43
best: 66 (Co-DETR)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D Object DetectiononCOCO test-dev
AP50· 2019-04-04
64
best: 82.1 (Plain-DETR (Swin-L))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D Object DetectiononCOCO test-dev
AP75· 2019-04-04
47
best: 71.7 (EVA)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D Object DetectiononCOCO test-dev
APL· 2019-04-04
54.6
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D Object DetectiononCOCO test-dev
APM· 2019-04-04
45.6
best: 67.7 (EVA)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D Object DetectiononCOCO test-dev
APS· 2019-04-04
25.3
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
2D Object DetectiononCOCO test-dev
box mAP· 2019-04-04
43
best: 66 (Co-DETR)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
16konCOCO test-dev
AP50· 2019-04-04
64
best: 82.1 (Plain-DETR (Swin-L))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
16konCOCO test-dev
AP75· 2019-04-04
47
best: 71.7 (EVA)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
16konCOCO test-dev
APL· 2019-04-04
54.6
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
16konCOCO test-dev
APM· 2019-04-04
45.6
best: 67.7 (EVA)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
16konCOCO test-dev
APS· 2019-04-04
25.3
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
16konCOCO test-dev
box mAP· 2019-04-04
43
best: 66 (Co-DETR)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701

Computer Vision6 results

Object DetectiononCOCO test-dev
AP50· 2019-04-04
64
best: 82.1 (Plain-DETR (Swin-L))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
Object DetectiononCOCO test-dev
AP75· 2019-04-04
47
best: 71.7 (EVA)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
Object DetectiononCOCO test-dev
APL· 2019-04-04
54.6
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
Object DetectiononCOCO test-dev
APM· 2019-04-04
45.6
best: 67.7 (EVA)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
Object DetectiononCOCO test-dev
APS· 2019-04-04
25.3
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701
Object DetectiononCOCO test-dev
box mAP· 2019-04-04
43
best: 66 (Co-DETR)
Libra R-CNN: Towards Balanced Learning for Object Detection arXiv:1904.02701