# Incremental Learning on ImageNet-100 B0, 20 steps (test)

Source: [Incremental Learning on ImageNet-100 B0, 20 steps (test)](<https://www.sota2.com/research/sota/incremental-learning-on-imagenet-100-b0-20-steps-test>)

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

Data updated: 2026-02-26T05:35:12.322Z

Evaluation of model performance on the ImageNet-100 dataset under the specific B0 configuration with 20 steps, tested on the test split, using Incremental Learning evaluation protocols.

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 | Incremental Learning |
| Dataset (including any stated split) | ImageNet-100 B0, 20 steps (test) |
| Metric | Average Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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/incremental-learning-on-imagenet-100-b0-20-steps-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Bound | 81.2 | Not recorded | 68fa6d181e209131cea37af3 |
| FOSTER | 74.49 | Not recorded | 68fa6d181e209131cea37af3 |
| DER | 73.79 | Not recorded | 68fa6d181e209131cea37af3 |
| WA | 63.2 | Not recorded | 68fa6d181e209131cea37af3 |
| iCaRL | 62.36 | Not recorded | 68fa6d181e209131cea37af3 |
| BiC | 58.93 | Not recorded | 68fa6d181e209131cea37af3 |
| PODNet | 53.69 | Not recorded | 68fa6d181e209131cea37af3 |

### Bound

Average Accuracy: 81.2. Result ID: 698f8db33a6c314849fa0cc9.

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

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

### FOSTER

Average Accuracy: 74.49. Result ID: 698f8db33a6c314849fa0ccf.

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

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

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

Recorded evaluation configuration: {"backbones":"single"}. This record does not assert independent reproduction.

### DER

Average Accuracy: 73.79. Result ID: 698f8db33a6c314849fa0cce.

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

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

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

Recorded evaluation configuration: {"backbones":"multiple (incremental backbones)"}. This record does not assert independent reproduction.

### WA

Average Accuracy: 63.2. Result ID: 698f8db33a6c314849fa0ccc.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa66aa1e209131cea117b4.md>)

Recorded evaluation configuration: {"backbones":"single"}. This record does not assert independent reproduction.

### iCaRL

Average Accuracy: 62.36. Result ID: 698f8db33a6c314849fa0cca.

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

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

Recorded evaluation configuration: {"backbones":"single"}. This record does not assert independent reproduction.

### BiC

Average Accuracy: 58.93. Result ID: 698f8db33a6c314849fa0ccb.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa65dc1e209131cea0ce26.md>)

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

Recorded evaluation configuration: {"backbones":"single"}. This record does not assert independent reproduction.

### PODNet

Average Accuracy: 53.69. Result ID: 698f8db33a6c314849fa0ccd.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa686b1e209131cea1bffa.md>)

[Implementation](<https://www.sota2.com/github.com/arthurdouillard/incremental_learning.pytorch>)

Recorded evaluation configuration: {"backbones":"single"}. This record does not assert independent reproduction.

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