CP-DETR-L Swin-L(with chunk)

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 minival
box AP· uses extra data· 2024-12-13
69.2
best: 72 (Co-DETR (single-scale))
CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection arXiv:2412.09799
2D ClassificationonLVIS v1.0 minival
box AP· uses extra data· 2024-12-13
69.2
best: 72 (Co-DETR (single-scale))
CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection arXiv:2412.09799
2D Object DetectiononLVIS v1.0 minival
box AP· uses extra data· 2024-12-13
69.2
best: 72 (Co-DETR (single-scale))
CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection arXiv:2412.09799
16konLVIS v1.0 minival
box AP· uses extra data· 2024-12-13
69.2
best: 72 (Co-DETR (single-scale))
CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection arXiv:2412.09799

Computer Vision1 result

Object DetectiononLVIS v1.0 minival
box AP· uses extra data· 2024-12-13
69.2
best: 72 (Co-DETR (single-scale))
CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection arXiv:2412.09799