Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Image Classification on ImageNet-1K (Token Accuracy & Efficiency)
Loading...
76.87
Accuracy (Patch Token)
Baseline
61.8108
65.7204
69.63
73.5396
Jun 17, 2026
Accuracy (Patch Token)
Accuracy (CLS Token)
FLOPs Saving (%)
Training Time Saving (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (Patch Token)
Accuracy (CLS Token)
FLOPs Saving (%)
Training Time Saving (%)
Baseline
Backbone=ViT-S, Teache...
2026.06
76.87
77.63
-
-
LEAP
Backbone=ViT-S, Teache...
2026.06
76.22
77.34
8.5
7.1
Baseline
Backbone=ViT-Tiny, Tea...
2026.06
63.35
64.4
-
-
LEAP
Backbone=ViT-Tiny, Tea...
2026.06
62.39
64.14
11.51
11.6
Feedback
Search any
task
Search any
task
