List your company
ResearchFormerly WizWand

Image Classification on CIFAR-100 Bucket 10 Forget

90.32AccuracyOriginal
-3.612820.773645.1669.5464Apr 9, 2026
Updated 7mo ago

Evaluation results

MethodLinks
OriginalEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.0490.32
OriginalEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.0490.08
OriginalEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.0489.58
Retain-only RetainEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.0487.82
Retain-only RetainEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.0481.88
Random-label with CMFEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.0453.06
Random-label with CMFEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.0452.54
NegGrad+ with CMFEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.0447.08
Salun with CMFEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.0446.4
Salun with CMFEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.0446.34
NegGrad+ with CMFEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.0445.28
Random-label with CMFEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.0441.1
Salun with CMFEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.0434.7
NegGrad+ with CMFEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.0422.3
Retain-only RetainEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.040