List your company
ResearchFormerly WizWand

Object Detection on ODinW-35

70.6APGrounding DINO 1.5 Pro
8.30424.47740.6556.823May 30, 2023Nov 18, 2023May 9, 2024Oct 29, 2024Apr 20, 2025Oct 10, 2025Apr 1, 2026
Updated 7mo ago

Evaluation results

MethodLinks
Grounding DINO 1.5 ProBackbone=ViT-L, Evaluation Protocol=fine-tuned2024.0570.6
DetCLIPv3Backbone=Swin-L2024.0570.4
DINO-Swin-LLanguage Query=false, Vision Query=false, Backbone=Swin-L, Pre-train Data=O365, Data Size=0.66M, Evaluation Setting=Full-Shot2023.0568.8
OmDetLanguage Query=true, Vision Query=false, Backbone=ConvNeXt-B, Pre-train Data=COCO, O365, LVIS, PhraseCut, Data Size=1.8M, Evaluation Setting=Full-Shot2023.0567.1
DINO-Swin-TLanguage Query=false, Vision Query=false, Backbone=Swin-T, Pre-train Data=O365, Data Size=0.66M, Evaluation Setting=Full-Shot2023.0566.7
MQ-GLIP-TLanguage Query=true, Vision Query=true, Backbone=Swin-T, Pre-train Data=O365+, Data Size=0.66M, Evaluation Setting=Full-Shot2023.0564.8
DyHead-TLanguage Query=false, Vision Query=false, Backbone=Swin-T, Pre-train Data=O365, Data Size=0.66M, Evaluation Setting=Full-Shot2023.0563.2
GLIP-TLanguage Query=true, Vision Query=false, Backbone=Swin-T, Pre-train Data=O365, GoldG, Cap4M, Data Size=5.5M, Evaluation Setting=Full-Shot2023.0562.6
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, V3Det2026.0450.6
PET-DINOOpen Source=Y, Prompt Type=Visual-I, Backbone=Swin-L, VLM sup.=-, Data Size=2.5M, Training Data=O365, OpenImages, V3Det2026.0449.7
PET-DINOOpen Source=Y, Prompt Type=Visual-I, Backbone=Swin-T, VLM sup.=-, Data Size=2.5M, Training Data=O365, OpenImages, V3Det2026.0448.3
MQ-GLIP-TLanguage Query=true, Vision Query=true, Backbone=Swin-T, Pre-train Data=O365+, Data Size=0.66M, Evaluation Setting=Few-Shot (3-shot)2023.0543
OmDetLanguage Query=true, Vision Query=false, Backbone=ConvNeXt-B, Pre-train Data=COCO, O365, LVIS, PhraseCut, Data Size=1.8M, Evaluation Setting=Few-Shot (3-shot)2023.0542.4
DINO-Swin-TLanguage Query=false, Vision Query=false, Backbone=Swin-T, Pre-train Data=O365, Data Size=0.66M, Evaluation Setting=Few-Shot (3-shot)2023.0541.2
CP-DETR-TOpen Source=N, Prompt Type=Visual-I, Backbone=Swin-T, VLM sup.=CLIP, Data Size=3.3M, Training Data=O365, OpenImages, GoldG, V3Det2026.0441
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-1B2026.0439.7
PET-DINOOpen Source=Y, Prompt Type=Visual-I, Backbone=Swin-L, VLM sup.=-, Data Size=0.6M, Training Data=O3652026.0439
GLIP-TLanguage Query=true, Vision Query=false, Backbone=Swin-T, Pre-train Data=O365, GoldG, Cap4M, Data Size=5.5M, Evaluation Setting=Few-Shot (3-shot)2023.0538.9
PET-DINOOpen Source=Y, Prompt Type=Visual-I, Backbone=Swin-T, VLM sup.=-, Data Size=0.6M, Training Data=O3652026.0438.8
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-1B2026.0437.7
DyHead-TLanguage Query=false, Vision Query=false, Backbone=Swin-T, Pre-train Data=O365, Data Size=0.66M, Evaluation Setting=Few-Shot (3-shot)2023.0537.5
Grounding DINO 1.5 ProBackbone=ViT-L [6], Pre-training data=Grounding-20M, Evaluation Protocol=Zero-shot2024.0530.2
Grounding DINO 1.5 ProBackbone=ViT-L, Evaluation Protocol=zero-shot2024.0530.2
Grounding DINOBackbone=Swin-L [19], Pre-training data=O365, OID, GoldG, Cap4M, COCO, RefC, Evaluation Protocol=Supervised2024.0529.4
PET-DINOOpen Source=Y, Prompt Type=Visual-G, Backbone=Swin-L, VLM sup.=-, Data Size=2.5M, Training Data=O365, OpenImages, V3Det2026.0428.6
MM-G-T(c3)Backbone=Swin-T, Zero-shot=true2024.0128.4
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-1B2026.0427.8
Grounding-DINOBackbone=Swin-L, Resolution=800*1333, #Params=343M, FPS=2.1, Zero-shot=true2025.1226.1
Grounding DINOPrompt Type=Text, Backbone=Swin-L, Training Data=O365, OpenImages, GoldG, Zero-shot=true2026.0426.1
WeDetect-LargeBackbone=ConvNext-L, Resolution=1280*1280, #Params=490M, FPS=6, Zero-shot=true2025.1225.8
PET-DINOOpen Source=Y, Prompt Type=Visual-G, Backbone=Swin-T, VLM sup.=-, Data Size=2.5M, Training Data=O365, OpenImages, V3Det2026.0425.5
DetCLIPBackbone=Swin-L, Resolution=800*1333, Zero-shot=true2025.1224.9
WeDetect-BaseBackbone=ConvNext-B, Resolution=640*640, #Params=176M, FPS=35.1, Zero-shot=true2025.1224.6
LLMDetBackbone=Swin-L, Resolution=1000*1560, #Params=343M, FPS=2.1, Zero-shot=true2025.1224.6
OWL-STBackbone=CLIP L/14 [23], Pre-training data=WebLI2B, Evaluation Protocol=Zero-shot2024.0524.4
PET-DINOOpen Source=Y, Prompt Type=Visual-G, Backbone=Swin-L, VLM sup.=-, Data Size=0.6M, Training Data=O3652026.0424.2
MQ-GLIP-LLanguage Query=true, Vision Query=true, Backbone=Swin-L, Pre-train Data=O365+, Data Size=0.66M, Evaluation Setting=Finetuning-free2023.0523.9
MQ-GLIPBackbone=Swin-L, Pre-training data=O365, Evaluation Protocol=Zero-shot2024.0523.9
MM-Grounding-DINOPrompt Type=Text, Backbone=Swin-L, Training Data=O365V2, OpenImage, GoldG, Zero-shot=true2026.0423.9
LLMDetBackbone=Swin-T, Zero-shot transfer=true2025.0123.8
LLMDetBackbone=Swin-T, Resolution=800*1333, #Params=172M, FPS=6, Zero-shot=true2025.1223.8
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-1B2026.0423.6
MM-GDINOBackbone=Swin-T, Zero-shot transfer=true2025.0123.1
MM-GDINOBackbone=Swin-T, Resolution=800*1333, #Params=172M, FPS=6, Zero-shot=true2025.1223.1
PET-DINOPrompt Type=Text, Backbone=Swin-L, Training Data=O365†, Zero-shot=true2026.0423.1
MM-G-T(c1)Backbone=Swin-T, Zero-shot=true2024.0122.8
MM-G-T(c2)Backbone=Swin-T, Zero-shot=true2024.0122.8
G-DINO-T(c)Backbone=Swin-T, Zero-shot=true2024.0122.7
Grounding-DINOBackbone=Swin-T, Zero-shot transfer=true2025.0122.7
Grounding-DINOBackbone=Swin-T, Resolution=800*1333, #Params=172M, FPS=6, Zero-shot=true2025.1222.7
GLIP-LLanguage Query=true, Vision Query=false, Backbone=Swin-L, Pre-train Data=FourODs, GoldG, Cap24M, Data Size=27.5M, Evaluation Setting=Finetuning-free2023.0522.6
ExpAlignBackbone=ConvNeXt-T, Pre-train Data=OG, #Params=60M, Resolution=640x640, Zero-shot=true2026.0122.6
MQ-GroundingDINO-TLanguage Query=true, Vision Query=true, Backbone=Swin-T, Pre-train Data=O365+, Data Size=0.66M, Evaluation Setting=Finetuning-free2023.0522.5
ExpAlignBackbone=ConvNeXt-T, Pre-train Data=OG, RefC, #Params=60M, Resolution=640x640, Zero-shot=true2026.0122.4
GLIPv2-TLanguage Query=true, Vision Query=false, Backbone=Swin-T, Pre-train Data=O365, GoldG, Cap4M, Data Size=5.5M, Evaluation Setting=Finetuning-free2023.0522.3
GLIPv2Backbone=Swin-T, Zero-shot transfer=true2025.0122.3
GDINO-TBackbone=Swin-T, Pre-train Data=OG, Cap4M, #Params=172M, Resolution=800x1333, Zero-shot=true2026.0122.3
Grounding DINOPrompt Type=Text, Backbone=Swin-T, Training Data=O365, GoldG, Cap4M, Zero-shot=true2026.0422.3
T-Rex2Backbone=Swin-L, Resolution=800*1333, Zero-shot=true2025.1222
T-Rex2 (visual)Backbone=Swin-L, Pre-training data=O365, OID, HierText, CrowdHuman, SA-1B, Evaluation Protocol=Zero-shot2024.0522
Grounding DINO-TLanguage Query=true, Vision Query=false, Backbone=Swin-T, Pre-train Data=O365, GoldG, Cap4M, Data Size=5.5M, Evaluation Setting=Finetuning-free2023.0521.7
MM-Grounding-DINOPrompt Type=Text, Backbone=Swin-T, Training Data=O365, GoldG, V3Det, Zero-shot=true2026.0421.4
WeDetect-TinyBackbone=ConvNext-T, Resolution=640*640, #Params=33M, FPS=62.5, Zero-shot=true2025.1221.1
MQ-GLIP-TLanguage Query=true, Vision Query=true, Backbone=Swin-T, Pre-train Data=O365+, Data Size=0.66M, Evaluation Setting=Finetuning-free2023.0520.8
PET-DINOPrompt Type=Text, Backbone=Swin-T, Training Data=O365†, Zero-shot=true2026.0420.6
PET-DINOOpen Source=Y, Prompt Type=Visual-G, Backbone=Swin-T, VLM sup.=-, Data Size=0.6M, Training Data=O3652026.0420.4
MM-G-T(b)Backbone=Swin-T, Zero-shot=true2024.0120.2
GLIPBackbone=Swin-T, Zero-shot transfer=true2025.0119.6
GLIPBackbone=Swin-T, Resolution=800*1333, #Params=232M, FPS=5.4, Zero-shot=true2025.1219.6
OWL-ViTLanguage Query=true, Vision Query=false, Backbone=ViT L/14(CLIP), Pre-train Data=O365, VG, Data Size=0.8M, Evaluation Setting=Finetuning-free2023.0518.8
OWL-ViTBackbone=ViT L/14(CLIP), Zero-shot transfer=true2025.0118.8
GLIP-TLanguage Query=true, Vision Query=false, Backbone=Swin-T, Pre-train Data=O365, GoldG, Cap4M, Data Size=5.5M, Evaluation Setting=Finetuning-free2023.0518.7
T-Rex2Backbone=Swin-T, Zero-shot transfer=true2025.0118
T-Rex2Backbone=Swin-T, Resolution=800*1333, Zero-shot=true2025.1218
YOLO-Worldv2-LBackbone=YOLOv8-L, Pre-train Data=OG, #Params=48M, Resolution=640x640, Zero-shot=true2026.0117.1
YOLO-World-LBackbone=YOLOv8-L, Resolution=640*640, #Params=48M, FPS=54.6, Zero-shot=true2025.1217.1
OmDetLanguage Query=true, Vision Query=false, Backbone=ConvNeXt-B, Pre-train Data=COCO, O365, LVIS, PhraseCut, Data Size=1.8M, Evaluation Setting=Finetuning-free2023.0516
MDETRLanguage Query=true, Vision Query=false, Backbone=ENB5, Pre-train Data=GoldG,RefC, Data Size=0.9M, Evaluation Setting=Finetuning-free2023.0510.7
MDETRBackbone=ENB5, Zero-shot transfer=true2025.0110.7