# Class-incremental learning on ImageNet-R T=10

Source: [Class-incremental learning on ImageNet-R T=10](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-t-10>)

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

Data updated: 2026-05-28T10:12:21.212Z

Evaluation of Class-Incremental Learning performance on the ImageNet-R dataset configured for 10 tasks (T=10), reporting ACC, MAA, and BWT metrics.

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 T=10 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-t-10.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Mean Average Accuracy](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-t-10.md?metric=Mean%20Average%20Accuracy>): Higher is better; unit: PERCENT.

- [Backward Transfer](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-t-10.md?metric=Backward%20Transfer>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Janus-LoRA | 75.78 | Not recorded | 6a17cc4ddbd7150506f81574 |
| BiLoRA | 73.93 | Not recorded | 6a17cc4ddbd7150506f81574 |
| InfLoRA | 73.9 | Not recorded | 6a17cc4ddbd7150506f81574 |
| LoRA-DRS | 72.58 | Not recorded | 6a17cc4ddbd7150506f81574 |
| Coda-Prompt | 71.59 | Not recorded | 6a17cc4ddbd7150506f81574 |
| LoRA-GPM | 71.56 | Not recorded | 6a17cc4ddbd7150506f81574 |
| L2P | 65.99 | Not recorded | 6a17cc4ddbd7150506f81574 |
| Dual-Prompt | 64.45 | Not recorded | 6a17cc4ddbd7150506f81574 |
| Fine-Tuning | 64.24 | Not recorded | 6a17cc4ddbd7150506f81574 |

### Janus-LoRA

Accuracy: 75.78. Result ID: 6a1813fefbc373592c126439.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc4ddbd7150506f81574.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc4ddbd7150506f81574.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### BiLoRA

Accuracy: 73.93. Result ID: 6a1813fefbc373592c126437.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc4ddbd7150506f81574.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### InfLoRA

Accuracy: 73.9. Result ID: 6a1813fefbc373592c126438.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc4ddbd7150506f81574.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### LoRA-DRS

Accuracy: 72.58. Result ID: 6a1813fefbc373592c126435.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc4ddbd7150506f81574.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77bc1e209131cea75057.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### Coda-Prompt

Accuracy: 71.59. Result ID: 6a1813fefbc373592c126434.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc4ddbd7150506f81574.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### LoRA-GPM

Accuracy: 71.56. Result ID: 6a1813fefbc373592c126436.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc4ddbd7150506f81574.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d07.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### L2P

Accuracy: 65.99. Result ID: 6a1813fefbc373592c126432.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc4ddbd7150506f81574.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### Dual-Prompt

Accuracy: 64.45. Result ID: 6a1813fefbc373592c126433.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc4ddbd7150506f81574.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### Fine-Tuning

Accuracy: 64.24. Result ID: 6a1813fefbc373592c126431.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc4ddbd7150506f81574.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

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