# Class-Incremental Learning on ImageNet-R Uniformly Mild scenario

Source: [Class-Incremental Learning on ImageNet-R Uniformly Mild scenario](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-uniformly-mild-scenario>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-17T07:21:01.545Z

Evaluation of Class-Incremental Learning performance on the ImageNet-R dataset under the Uniformly Mild scenario, reporting Average Accuracy.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Class-Incremental Learning |
| Dataset (including any stated split) | ImageNet-R Uniformly Mild scenario |
| Metric | Average Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Average Accuracy](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-uniformly-mild-scenario.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Forgetting](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-uniformly-mild-scenario.md?metric=Average%20Forgetting>): Lower is better; unit: PERCENT.

- [Rank](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-uniformly-mild-scenario.md?metric=Rank>): Lower is better; unit: SCALAR.

- [Average Rank](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-uniformly-mild-scenario.md?metric=Average%20Rank>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Average Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PROTEUS | 82.17 | Not recorded | 69b8e0040636e5bf4afbe95f |
| RanPAC | 78.08 | Not recorded | 69b8e0040636e5bf4afbe95f |
| SD-LoRA | 75.81 | Not recorded | 69b8e0040636e5bf4afbe95f |
| CODAPrompt | 75.39 | Not recorded | 69b8e0040636e5bf4afbe95f |
| InfLoRA | 74.55 | Not recorded | 69b8e0040636e5bf4afbe95f |
| HiDe-Prompt | 73 | Not recorded | 69b8e0040636e5bf4afbe95f |
| DualPrompt | 69.38 | Not recorded | 69b8e0040636e5bf4afbe95f |
| SPrompt | 67.71 | Not recorded | 69b8e0040636e5bf4afbe95f |
| AdaPromptCL | 65.63 | Not recorded | 69b8e0040636e5bf4afbe95f |
| L2P | 61.48 | Not recorded | 69b8e0040636e5bf4afbe95f |

### PROTEUS

Average Accuracy: 82.17. Result ID: 69b900d647f34ce924a112a5.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RanPAC

Average Accuracy: 78.08. Result ID: 69b900d647f34ce924a112a4.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71cb1e209131cea53052.md>)

[Implementation](<https://github.com/RanPAC/RanPAC>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SD-LoRA

Average Accuracy: 75.81. Result ID: 69b900d647f34ce924a112a3.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77461e209131cea7225e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CODAPrompt

Average Accuracy: 75.39. Result ID: 69b900d647f34ce924a1129e.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee41e209131cea42add.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### InfLoRA

Average Accuracy: 74.55. Result ID: 69b900d647f34ce924a112a2.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72bb1e209131cea58354.md>)

[Implementation](<https://github.com/liangyanshuo/InfLoRA>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HiDe-Prompt

Average Accuracy: 73. Result ID: 69b900d647f34ce924a112a1.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d81e209131cea4d9f3.md>)

[Implementation](<https://github.com/thu-ml/HiDe-Prompt>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DualPrompt

Average Accuracy: 69.38. Result ID: 69b900d647f34ce924a1129d.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d341e209131cea38614.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SPrompt

Average Accuracy: 67.71. Result ID: 69b900d647f34ce924a1129f.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ece1e209131cea424c2.md>)

[Implementation](<https://github.com/iamwangyabin/S-Prompts>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AdaPromptCL

Average Accuracy: 65.63. Result ID: 69b900d647f34ce924a112a0.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60717.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### L2P

Average Accuracy: 61.48. Result ID: 69b900d647f34ce924a1129c.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0040636e5bf4afbe95f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0c1e209131cea31ad7.md>)

[Implementation](<https://github.com/google-research/l2p>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.