FRACAL-SwinT

Reported on 2 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 Vision2 results

Instance SegmentationonLVIS v1.0 val
mask AP· 2024-10-15
30.7
best: 60.7 (Co-DETR (single-scale))
Fractal Calibration for long-tailed object detection arXiv:2410.11774
Instance SegmentationonLVIS v1.0 val
mask APr· 2024-10-15
25.7
best: 45.8 (DiverGen (Swin-L))
Fractal Calibration for long-tailed object detection arXiv:2410.11774