Image Classification on CIFAR-100 Bucket 10 Retain
90.13AccuracyRetain-only Retain
Evaluation results
| Method | Links | |
|---|---|---|
| Retain-only RetainEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 90.13 | |
| Retain-only RetainEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 90.1 | |
| OriginalEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 90.09 | |
| OriginalEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 89.94 | |
| OriginalEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 89.67 | |
| Retain-only RetainEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 89.31 | |
| Random-label with CMFEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 87.81 | |
| Random-label with CMFEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 87.79 | |
| Salun with CMFEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 87.42 | |
| Salun with CMFEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 87.39 | |
| Random-label with CMFEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 86.01 | |
| Salun with CMFEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 85.37 | |
| NegGrad+ with CMFEvaluation Head=NCC, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 83.97 | |
| NegGrad+ with CMFEvaluation Head=Output, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 83.91 | |
| NegGrad+ with CMFEvaluation Head=Linear Probe, Backbone=ViT-S/16, Pre-training=ImageNet2026.04 | 81.19 |