# Exemplar-Free Class-Incremental Learning on ImageNet-R 10-task (test)

Source: [Exemplar-Free Class-Incremental Learning on ImageNet-R 10-task (test)](<https://www.sota2.com/research/sota/exemplar-free-class-incremental-learning-on-imagenet-r-10-task-test>)

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

Data updated: 2026-03-24T14:25:15.283Z

Evaluation of model performance on the test split of the ImageNet-R 10-task benchmark under an Exemplar-Free Class-Incremental Learning setting.

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 | Exemplar-Free Class-Incremental Learning |
| Dataset (including any stated split) | ImageNet-R 10-task (test) |
| Metric | Average Accuracy (AA) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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 (AA)](<https://www.sota2.com/research/sota/exemplar-free-class-incremental-learning-on-imagenet-r-10-task-test.md?metric=Average%20Accuracy%20(AA)>): Higher is better; unit: PERCENT.

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

- [Forward Metric (FM)](<https://www.sota2.com/research/sota/exemplar-free-class-incremental-learning-on-imagenet-r-10-task-test.md?metric=Forward%20Metric%20(FM)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Accuracy (AA) | Result date | Report paper |
| --- | --- | --- | --- |
| Inf-SSM | 27.92 | Not recorded | 68fa78c91e209131cea7a86b |
| LwF-ABC | 26.17 | Not recorded | 68fa78c91e209131cea7a86b |
| EWC | 23.14 | Not recorded | 68fa78c91e209131cea7a86b |
| MAS | 22.41 | Not recorded | 68fa78c91e209131cea7a86b |
| Seq | 17.58 | Not recorded | 68fa78c91e209131cea7a86b |
| SI | 17.15 | Not recorded | 68fa78c91e209131cea7a86b |

### Inf-SSM

Average Accuracy (AA): 27.92. Result ID: 69c29eba47f34ce924ab4089.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c91e209131cea7a86b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c91e209131cea7a86b.md>)

Recorded evaluation configuration: {"Backbone":"Vim-tiny"}. This record does not assert independent reproduction.

### LwF-ABC

Average Accuracy (AA): 26.17. Result ID: 69c29eba47f34ce924ab4088.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c91e209131cea7a86b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63201e209131ce9fd0b3.md>)

Recorded evaluation configuration: {"Backbone":"Vim-tiny","Regularization focus":"parameter sets (A, B, C)"}. This record does not assert independent reproduction.

### EWC

Average Accuracy (AA): 23.14. Result ID: 69c29eba47f34ce924ab4085.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c91e209131cea7a86b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3555e.md>)

Recorded evaluation configuration: {"Backbone":"Vim-tiny","Regularization focus":"parameter sets (A, B, C)"}. This record does not assert independent reproduction.

### MAS

Average Accuracy (AA): 22.41. Result ID: 69c29eba47f34ce924ab4087.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c91e209131cea7a86b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e61e209131cea073fa.md>)

Recorded evaluation configuration: {"Backbone":"Vim-tiny","Regularization focus":"parameter sets (A, B, C)"}. This record does not assert independent reproduction.

### Seq

Average Accuracy (AA): 17.58. Result ID: 69c29eba47f34ce924ab4084.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c91e209131cea7a86b.md>)

Recorded evaluation configuration: {"Backbone":"Vim-tiny","Regularization focus":"parameter sets (A, B, C)"}. This record does not assert independent reproduction.

### SI

Average Accuracy (AA): 17.15. Result ID: 69c29eba47f34ce924ab4086.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c91e209131cea7a86b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5ed01e209131ce9e565c.md>)

Recorded evaluation configuration: {"Backbone":"Vim-tiny","Regularization focus":"parameter sets (A, B, C)"}. This record does not assert independent reproduction.

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