List your company

Object Detection on OV-LVIS v1.0 (test)

34.9mAPrF-ViT+CLIPSelf
10.56416.88223.229.518Oct 2, 2023

Evaluation results

MethodLinks
F-ViT+CLIPSelfBackbone=ViT-L/14, Feature Source=Image Patch2023.1034.934.635.635.1
RO-ViTBackbone=ViT-H/162023.1034.1——35.1
CFM-ViTBackbone=ViT-L/162023.1033.9——36.6
DeticBackbone=SwinB2023.1033.8——47
F-VLMBackbone=RN50x642023.1032.8——34.9
RO-ViTBackbone=ViT-L/162023.1032.1——34
F-VLMBackbone=RN50x162023.1030.4——32.1
CORA+Backbone=RN50x4, learnable category prompt=true, open-vocabulary ability from additional image annotations=true2023.1028.1———
RO-ViTBackbone=ViT-B/162023.1028——30.2
VLDetBackbone=SwinB2023.1026.339.441.938.1
F-VLMBackbone=RN50x42023.1026.3——28.5
OWL-ViTBackbone=ViT-L/142023.1025.6——34.7
F-ViT+CLIPSelfBackbone=ViT-B/16, Feature Source=Image Patch2023.1025.321.829.125.2
DeticBackbone=RN502023.1024.9——32.4
F-ViTBackbone=ViT-L/142023.1024.227.931.528.7
BARON-KDBackbone=RN50, learnable category prompt=true2023.1022.627.629.827.6
CORABackbone=RN50x4, learnable category prompt=true2023.1022.2———
RegionCLIPBackbone=RN50x42023.102232.136.932.3
VLDetBackbone=RN502023.1021.729.834.330.1
OADPBackbone=RN502023.1021.726.32926.6
OC-OVDBackbone=RN50, open-vocabulary ability from additional image annotations=true2023.1021.12529.125.9
DetProBackbone=RN50, learnable category prompt=true2023.1019.825.628.925.9
F-VLMBackbone=RN502023.1018.6——24.2
OV-DETRBackbone=RN502023.1017.42532.526.6
RegionCLIPBackbone=RN502023.1017.127.43428.2
ViLDBackbone=RN502023.1016.624.630.325.5
F-ViTBackbone=ViT-B/162023.1011.512.320.615.4