List your company
ResearchFormerly WizWand

Open-vocabulary Object Detection on LVIS v1 (val)

47.2AP_r^bOWL-ST+FT
1624.132.240.3May 11, 2023May 30, 2023Jun 18, 2023Jul 7, 2023Jul 26, 2023Aug 14, 2023Sep 2, 2023
Updated 8mo ago

Evaluation results

MethodLinks
OWL-ST+FTBackbone=SigLIP G/14, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, LVISbase, Vocabulary Access Protocol=Open vocabulary2023.0647.247
OWL-ST+FTBackbone=CLIP L/14, Self-training data=WebLI, Self-training vocabulary=N-grm+curated, Human box annotations=O+VG, LVISbase, Vocabulary Access Protocol=Human-curated vocabulary2023.0645.950.4
OWL-ST+FTBackbone=CLIP L/14, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, LVISbase, Vocabulary Access Protocol=Open vocabulary2023.0644.649.4
OWL-ST+FTBackbone=CLIP B/16, Self-training data=WebLI, Self-training vocabulary=N-grm+curated, Human box annotations=O+VG, LVISbase, Vocabulary Access Protocol=Human-curated vocabulary2023.0640.545.6
OWL-STBackbone=SigLIP G/14, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, Vocabulary Access Protocol=Open vocabulary2023.0637.533.7
OWL-ST+FTBackbone=CLIP B/16, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, LVISbase, Vocabulary Access Protocol=Open vocabulary2023.0636.241.8
CFM-ViTpretrained model=ViT-L/16, detector backbone=ViT-L/16, Annotation=Box AP2023.0935.638.5
RO-ViTpretrained model=ViT-H/16, detector backbone=ViT-H/16, evaluation protocol=box AP2023.0535.137.4
OWL-STBackbone=CLIP L/14, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, Vocabulary Access Protocol=Open vocabulary2023.0634.933.5
RO-ViTpretrained model=ViT-H/16, detector backbone=ViT-H/16, evaluation protocol=mask AP2023.0534.135.1
CFM-ViTpretrained model=ViT-L/16, detector backbone=ViT-L/16, Annotation=Mask AP2023.0933.936.6
RO-ViTpretrained model=ViT-L/16, detector backbone=ViT-L/16, evaluation protocol=box AP2023.0533.636.2
DetCLIPv2Backbone=Swin-L, Self-training data=CC15M, Self-training vocabulary=Nouns+curated, Human box annotations=O365+GoldG, Vocabulary Access Protocol=Human-curated vocabulary2023.0633.336.6
F-VLMBackbone=R50x64, Human box annotations=LVISbase, Vocabulary Access Protocol=Open vocabulary2023.0632.834.9
RO-ViTpretrained model=ViT-L/16, detector backbone=ViT-L/16, pre-training dataset=LAION-2B, evaluation protocol=mask AP2023.0532.432.9
RO-ViTpretrained model=ViT-L/16, detector backbone=ViT-L/16, evaluation protocol=mask AP2023.0532.134
RO-ViTpretrained model=ViT-L/14, detector backbone=ViT-L/14, evaluation protocol=mask AP2023.0531.434
OWLBackbone=CLIP L/14, Human box annotations=O365+VG, Vocabulary Access Protocol=Open vocabulary2023.0631.234.6
DetCLIPv2Backbone=Swin-T, Self-training data=CC15M, Self-training vocabulary=Nouns+curated, Human box annotations=O365+GoldG, Vocabulary Access Protocol=Human-curated vocabulary2023.063132.8
3WaysBackbone=NFNet-F6, Self-training data=CC12M, Self-training vocabulary=captions, Human box annotations=LVISbase, Vocabulary Access Protocol=Open vocabulary2023.0630.144.6
CFM-ViTpretrained model=ViT-B/16, detector backbone=ViT-B/16, Annotation=Box AP2023.0929.633.8
OWL-STBackbone=CLIP B/16, Self-training data=WebLI, Self-training vocabulary=N-grams, Human box annotations=O+VG, Vocabulary Access Protocol=Open vocabulary2023.0629.627
CFM-ViTpretrained model=ViT-B/16, detector backbone=ViT-B/16, Annotation=Mask AP2023.0928.832
RO-ViTpretrained model=ViT-B/16, detector backbone=ViT-B/16, evaluation protocol=box AP2023.0528.431.9
RO-ViTpretrained model=ViT-B/16, detector backbone=ViT-B/16, evaluation protocol=mask AP2023.052830.2
ViLD-Enspretrained model=EffNet-B7, detector backbone=EffNet-B7, evaluation protocol=mask AP2023.0526.329.3
ViLD-Enspretrained model=EffNet-B7, detector backbone=EffNet-B7, Annotation=Mask AP2023.0926.329.3
F-VLMBackbone=R50x4, Human box annotations=LVISbase, Vocabulary Access Protocol=Open vocabulary2023.0626.328.5
OWL-ViTpretrained model=ViT-L/14, detector backbone=ViT-L/14, evaluation protocol=box AP2023.0525.634.7
OWL-ViTpretrained model=ViT-L/14, detector backbone=ViT-L/14, Annotation=Box AP2023.0925.634.7
3WaysBackbone=NFNet-F0, Self-training data=CC12M, Self-training vocabulary=captions, Human box annotations=LVISbase, Vocabulary Access Protocol=Open vocabulary2023.0625.635.7
Detic-CN2pretrained model=ViT-B/32, detector backbone=R-50, evaluation protocol=mask AP2023.0524.632.4
Detic-CN2pretrained model=ViT-B/32, detector backbone=R-50, Annotation=Mask AP2023.0924.632.4
DeticBackbone=R50, Self-training data=IN-21k, Self-training vocabulary=LVIS classes, Human box annotations=LVISbase, Vocabulary Access Protocol=Human-curated vocabulary2023.0624.632.4
OWL-ViTpretrained model=ViT-H/14, detector backbone=ViT-H/14, evaluation protocol=box AP2023.0523.335.3
OWL-ViTpretrained model=ViT-H/14, detector backbone=ViT-H/14, Annotation=Box AP2023.0923.335.3
RegionCLIPpretrained model=R-50x4, detector backbone=R-50x4, evaluation protocol=mask AP2023.052232.3
RegionCLIPpretrained model=R-50x4, detector backbone=R-50x4, Annotation=Mask AP2023.092232.3
RegionCLIPBackbone=R50x4, Self-training data=CC3M, Self-training vocabulary=6k concepts, Human box annotations=LVISbase, Vocabulary Access Protocol=Open vocabulary2023.062232.3
ViLD-Enspretrained model=ViT-L/14, detector backbone=EffNet-B7, evaluation protocol=mask AP2023.0521.729.6
ViLD-Enspretrained model=ViT-L/14, detector backbone=EffNet-B7, Annotation=Mask AP2023.0921.729.6
PromptDetpretrained model=ViT-B/32, detector backbone=R-50, evaluation protocol=mask AP2023.0521.425.3
PromptDetpretrained model=ViT-B/32, detector backbone=R-50, Annotation=Mask AP2023.0921.425.3
Rasheed et al.pretrained model=ViT-B/32, detector backbone=R-50, evaluation protocol=mask AP2023.0521.125.9
Rasheed et al.pretrained model=ViT-B/32, detector backbone=R-50, Annotation=Mask AP2023.0921.125.9
OWLBackbone=CLIP B/16, Human box annotations=O365+VG, Vocabulary Access Protocol=Open vocabulary2023.0620.627.2
DetPro-Cascadepretrained model=ViT-B/32, detector backbone=R-50, evaluation protocol=mask AP2023.052027
DetPro-Cascadepretrained model=ViT-B/32, detector backbone=R-50, Annotation=Mask AP2023.092027
ViLD-Enspretrained model=ViT-B/32, detector backbone=R-152, evaluation protocol=mask AP2023.0518.726
ViLD-Enspretrained model=ViT-B/32, detector backbone=R-152, Annotation=Mask AP2023.0918.726
OV-DETRpretrained model=ViT-B/32, detector backbone=R-50, evaluation protocol=mask AP2023.0517.426.6
OV-DETRpretrained model=ViT-B/32, detector backbone=R-50, Annotation=Mask AP2023.0917.426.6
VL-PLMpretrained model=ViT-B/32, detector backbone=R-50, evaluation protocol=mask AP2023.0517.227
VL-PLMpretrained model=ViT-B/32, detector backbone=R-50, Annotation=Mask AP2023.0917.227