List your company

Object Detection on COCO (AP)

68.4APCP-DETR-L*
37.245.353.461.5Apr 1, 2026Apr 6, 2026Apr 12, 2026Apr 18, 2026Apr 23, 2026Apr 29, 2026May 5, 2026

Evaluation results

MethodLinks
CP-DETR-L*Open Source=N, Prompt Type=Visual-I, Backbone=Swin-L, VLM sup.=CLIP, Data Size=3.3M, Training Data=O365, OpenImages, GoldG, V3Det2026.0468.4
PET-DINOOpen Source=Y, Prompt Type=Visual-I, Backbone=Swin-L, VLM sup.=-, Data Size=2.5M, Training Data=O365, OpenImages, V3Det2026.0466.5
PET-DINOOpen Source=Y, Prompt Type=Visual-I, Backbone=Swin-L, VLM sup.=-, Data Size=0.6M, Training Data=O3652026.0466.4
PET-DINOOpen Source=Y, Prompt Type=Visual-I, Backbone=Swin-T, VLM sup.=-, Data Size=2.5M, Training Data=O365, OpenImages, V3Det2026.0464.3
PET-DINOOpen Source=Y, Prompt Type=Visual-I, Backbone=Swin-T, VLM sup.=-, Data Size=0.6M, Training Data=O3652026.0464
CP-DETR-TOpen Source=N, Prompt Type=Visual-I, Backbone=Swin-T, VLM sup.=CLIP, Data Size=3.3M, Training Data=O365, OpenImages, GoldG, V3Det2026.0461.8
T-Rex2Open Source=N, Prompt Type=Visual-I, Backbone=Swin-L, VLM sup.=CLIP, Data Size=3.1M, Training Data=O365, OpenImages, HierText, CrowdHuman, SA-1B2026.0458.5
VL-SAM-v3Backbone=Swin-T2026.0556.8
T-Rex2Open Source=N, Prompt Type=Visual-I, Backbone=Swin-T, VLM sup.=CLIP, Data Size=3.1M, Training Data=O365, OpenImages, HierText, CrowdHuman, SA-1B2026.0456.6
VL-SAM-v2Backbone=Swin-T2026.0556
LLMDetBackbone=Swin-T2026.0555.6
MM-GDINOBackbone=Swin-T2026.0550.4
Grounding-DINOBackbone=Swin-T2026.0548.4
DetCLIPv3Backbone=Swin-T2026.0547.2
PET-DINOOpen Source=Y, Prompt Type=Visual-G, Backbone=Swin-L, VLM sup.=-, Data Size=0.6M, Training Data=O3652026.0446.7
T-Rex2Open Source=N, Prompt Type=Visual-G, Backbone=Swin-L, VLM sup.=CLIP, Data Size=3.1M, Training Data=O365, OpenImages, HierText, CrowdHuman, SA-1B2026.0446.5
GLIPBackbone=Swin-T2026.0546.1
PET-DINOOpen Source=Y, Prompt Type=Visual-G, Backbone=Swin-L, VLM sup.=-, Data Size=2.5M, Training Data=O365, OpenImages, V3Det2026.0444.3
PET-DINOOpen Source=Y, Prompt Type=Visual-G, Backbone=Swin-T, VLM sup.=-, Data Size=0.6M, Training Data=O3652026.0440.3
T-Rex2Open Source=N, Prompt Type=Visual-G, Backbone=Swin-T, VLM sup.=CLIP, Data Size=3.1M, Training Data=O365, OpenImages, HierText, CrowdHuman, SA-1B2026.0438.8
PET-DINOOpen Source=Y, Prompt Type=Visual-G, Backbone=Swin-T, VLM sup.=-, Data Size=2.5M, Training Data=O365, OpenImages, V3Det2026.0438.4