SimLTD w/MixPL (Swin-L + COCO unlabeled images)

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

3DonLVIS v1.0 val
box AP· uses extra data· 2024-12-28
51.5
best: 68 (Co-DETR (single-scale))
SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection arXiv:2412.20047
2D ClassificationonLVIS v1.0 val
box AP· uses extra data· 2024-12-28
51.5
best: 68 (Co-DETR (single-scale))
SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection arXiv:2412.20047
2D Object DetectiononLVIS v1.0 val
box AP· uses extra data· 2024-12-28
51.5
best: 68 (Co-DETR (single-scale))
SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection arXiv:2412.20047
16konLVIS v1.0 val
box AP· uses extra data· 2024-12-28
51.5
best: 68 (Co-DETR (single-scale))
SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection arXiv:2412.20047

Computer Vision1 result

Object DetectiononLVIS v1.0 val
box AP· uses extra data· 2024-12-28
51.5
best: 68 (Co-DETR (single-scale))
SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection arXiv:2412.20047