E2EC DLA-34

Reported on 3 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Instance SegmentationonCOCO test-dev
AP50· 2022-03-08
52.9
best: 80.8 (InternImage-H)
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation arXiv:2203.04074
Instance SegmentationonCOCO test-dev
AP75· 2022-03-08
35.9
best: 63.4 (Co-DETR)
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation arXiv:2203.04074
Instance SegmentationonCOCO test-dev
mask AP· 2022-03-08
33.8
best: 57.1 (Co-DETR)
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation arXiv:2203.04074