Class-Incremental Learning on ImageNet-R Uniformly Mild scenario
82.17Average AccuracyPROTEUS
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| PROTEUS2026.01 | 82.17 | — | — | — | |
| RanPAC2026.01 | 78.08 | — | — | — | |
| SD-LoRA2026.01 | 75.81 | — | — | — | |
| CODAPrompt2026.01 | 75.39 | — | — | — | |
| InfLoRA2026.01 | 74.55 | — | — | — | |
| HiDe-Prompt2026.01 | 73 | — | — | — | |
| DualPrompt2026.01 | 69.38 | — | — | — | |
| SPrompt2026.01 | 67.71 | — | — | — | |
| AdaPromptCL2026.01 | 65.63 | — | — | — | |
| L2P2026.01 | 61.48 | — | — | — | |
| CODAPromptScenario=Uniformly Mild, Backbone=ViT-B/16, Pre-trained=ImageNet-21k fine-tuned on ImageNet-1K2026.01 | — | 1.61 | 2 | 3.17 | |
| DualPromptScenario=Uniformly Mild, Backbone=ViT-B/16, Pre-trained=ImageNet-21k fine-tuned on ImageNet-1K2026.01 | — | 5.39 | 5 | 4.83 | |
| L2PScenario=Uniformly Mild, Backbone=ViT-B/16, Pre-trained=ImageNet-21k fine-tuned on ImageNet-1K2026.01 | — | 7.93 | 6 | 5.67 | |
| PROTEUSScenario=Uniformly Mild, Backbone=ViT-B/16, Pre-trained=ImageNet-21k fine-tuned on ImageNet-1K, LoRA rank r=42026.01 | — | 1.45 | 1 | 2.17 | |
| RanPACScenario=Uniformly Mild, Backbone=ViT-B/16, Pre-trained=ImageNet-21k fine-tuned on ImageNet-1K2026.01 | — | 4.55 | 4 | 2.5 | |
| SPromptScenario=Uniformly Mild, Backbone=ViT-B/16, Pre-trained=ImageNet-21k fine-tuned on ImageNet-1K2026.01 | — | 3.32 | 3 | 2.67 |