RelationNet++ (ResNeXt-64x4d-101-DCN)

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· 2020-10-29
52.7
best: 66 (Co-DETR)
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder arXiv:2010.15831
2D ClassificationonCOCO test-dev
box mAP· 2020-10-29
52.7
best: 66 (Co-DETR)
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder arXiv:2010.15831
2D Object DetectiononCOCO test-dev
box mAP· 2020-10-29
52.7
best: 66 (Co-DETR)
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder arXiv:2010.15831
16konCOCO test-dev
box mAP· 2020-10-29
52.7
best: 66 (Co-DETR)
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder arXiv:2010.15831

Computer Vision1 result

Object DetectiononCOCO test-dev
box mAP· 2020-10-29
52.7
best: 66 (Co-DETR)
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder arXiv:2010.15831