Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Image Classification on Small CIFAR-5 (test)
Loading...
99.96
Retention Accuracy (%)
Re-train
92.3784
94.3467
96.315
98.2833
Jan 29, 2026
Retention Accuracy (%)
Unlearning Accuracy (%)
Test Accuracy (%)
MIA Accuracy (%)
Average Gap
Re-learn Time (Epochs)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Retention Accuracy (%)
Unlearning Accuracy (%)
Test Accuracy (%)
MIA Accuracy (%)
Average Gap
Re-learn Time (Epochs)
Re-train
Backbone=ResNet-18
2026.01
99.96
8.33
94.8
27
0
3.33
Original
Backbone=ResNet-18
2026.01
99.93
0
95.37
4.67
7.82
-
NTK
Backbone=ResNet-18
2026.01
99.93
7
95.37
16
3.23
4.67
CR
Backbone=ResNet-18
2026.01
99.56
14
91.8
58.17
10.06
-
RURK
Backbone=ResNet-18
2026.01
99.52
5.67
93.83
33.33
2.6
2
Fisher
Backbone=ResNet-18
2026.01
92.67
12.67
88.8
47.33
9.49
3
Feedback
Search any
task
Search any
task
