Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Context-dependent Visual Reasoning on Bongard-HOI (test)
Loading...
66.39
Accuracy (Seen Act, Seen Obj)
TPT
49.3756
53.7928
58.21
62.6272
Sep 15, 2022
Accuracy (Seen Act, Seen Obj)
Accuracy (Unseen Act, Seen Obj)
Accuracy (Seen Act, Unseen Obj)
Accuracy (Unseen Act, Unseen Obj)
Average Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy (Seen Act, Seen Obj)
Accuracy (Unseen Act, Seen Obj)
Accuracy (Seen Act, Unseen Obj)
Accuracy (Unseen Act, Unseen Obj)
Average Accuracy
TPT
Backbone=CLIP-RN50
2022.09
66.39
68.5
65.98
65.48
66.59
HOITrans
2022.09
59.5
64.38
63.1
62.87
62.46
Meta-baseline
Backbone=ResNet-50, Gr...
2022.09
58.82
58.75
58.56
57.04
58.3
CNN-baseline
Backbone=ResNet-50
2022.09
50.03
49.89
49.77
50.01
49.92
Feedback
Search any
task
Search any
task