ResNet-50-FPN Mask R-CNN + KL Loss + var voting + soft-NMS

Reported on 5 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.

Methodology4 results

3DonCOCO test-dev
box mAP· 2018-09-23
40.4
best: 66 (Co-DETR)
Bounding Box Regression with Uncertainty for Accurate Object Detection arXiv:1809.08545
2D ClassificationonCOCO test-dev
box mAP· 2018-09-23
40.4
best: 66 (Co-DETR)
Bounding Box Regression with Uncertainty for Accurate Object Detection arXiv:1809.08545
2D Object DetectiononCOCO test-dev
box mAP· 2018-09-23
40.4
best: 66 (Co-DETR)
Bounding Box Regression with Uncertainty for Accurate Object Detection arXiv:1809.08545
16konCOCO test-dev
box mAP· 2018-09-23
40.4
best: 66 (Co-DETR)
Bounding Box Regression with Uncertainty for Accurate Object Detection arXiv:1809.08545

Computer Vision1 result

Object DetectiononCOCO test-dev
box mAP· 2018-09-23
40.4
best: 66 (Co-DETR)
Bounding Box Regression with Uncertainty for Accurate Object Detection arXiv:1809.08545