# Class Incremental Learning on ImageNet-100 Base 50 Inc 10 1.0 (test)

Source: [Class Incremental Learning on ImageNet-100 Base 50 Inc 10 1.0 (test)](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-100-base-50-inc-10-1-0-test>)

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

Data updated: 2026-03-10T13:12:31.653Z

Evaluation of model performance on the test split of ImageNet-100 version 1.0 under a Class Incremental Learning setting configured for Base 50 and Increment 10, reporting Last and 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-100 Base 50 Inc 10 1.0 (test) |
| Metric | Last 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

- [Last Accuracy](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-100-base-50-inc-10-1-0-test.md?metric=Last%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-100-base-50-inc-10-1-0-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Last Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GRACE | 73.5 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| DER | 73.34 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| FOSTER | 67.4 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| DGR | 65.15 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| MEMO | 60.16 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| ICARL | 53.96 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| REPLAY | 41.46 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| EWC | 11.68 | Not recorded | 69afa5bf2d603e6de3e43f2a |
| FINETUNE | 9.58 | Not recorded | 69afa5bf2d603e6de3e43f2a |

### GRACE

Last Accuracy: 73.5. Result ID: 69b018a86dbb7075b95a2ca4.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

Recorded evaluation configuration: {"#P":"44.68"}. This record does not assert independent reproduction.

### DER

Last Accuracy: 73.34. Result ID: 69b018a86dbb7075b95a2ca0.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699b1e209131cea23084.md>)

[Implementation](<https://github.com/Rhyssiyan/DER-ClassIL.pytorch>)

Recorded evaluation configuration: {"#P":"67.02"}. This record does not assert independent reproduction.

### FOSTER

Last Accuracy: 67.4. Result ID: 69b018a86dbb7075b95a2ca1.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d181e209131cea37af3.md>)

[Implementation](<https://github.com/G-U-N/ECCV22-FOSTER>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

### DGR

Last Accuracy: 65.15. Result ID: 69b018a86dbb7075b95a2ca3.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72bb1e209131cea58382.md>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

### MEMO

Last Accuracy: 60.16. Result ID: 69b018a86dbb7075b95a2ca2.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8c1e209131cea407e9.md>)

Recorded evaluation configuration: {"#P":"53.14"}. This record does not assert independent reproduction.

### ICARL

Last Accuracy: 53.96. Result ID: 69b018a86dbb7075b95a2c9f.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634e1e209131ce9fded4.md>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

### REPLAY

Last Accuracy: 41.46. Result ID: 69b018a86dbb7075b95a2c9d.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

### EWC

Last Accuracy: 11.68. Result ID: 69b018a86dbb7075b95a2c9e.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

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

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

### FINETUNE

Last Accuracy: 9.58. Result ID: 69b018a86dbb7075b95a2c9c.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bf2d603e6de3e43f2a.md>)

Recorded evaluation configuration: {"#P":"11.17"}. This record does not assert independent reproduction.

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