List your company
ResearchFormerly WizWand

Image Classification on CIFAR-100 Bucket 1 Forget

93AccuracyOriginal
-3.7221.3946.571.61Apr 9, 2026
Updated 7mo ago

Evaluation results

MethodLinks
OriginalEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.0493
OriginalEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.0492.2
OriginalEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.0492
Retain-only RetainEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.0490.8
Retain-only RetainEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.0487.8
NegGrad+ with CMFEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.0458.4
NegGrad+ with CMFEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.0455.8
Random-label with CMFEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.0455.2
Random-label with CMFEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.0455.2
Salun with CMFEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.0453.2
Salun with CMFEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.0451.2
Random-label with CMFEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.0424.6
NegGrad+ with CMFEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.0424.4
Salun with CMFEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.0423.2
Retain-only RetainEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.040