# Class Incremental Learning on ImageNet100-B0 (10 steps, non-rehearsal)

Source: [Class Incremental Learning on ImageNet100-B0 (10 steps, non-rehearsal)](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet100-b0-10-steps-non-rehearsal>)

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

Data updated: 2026-02-26T05:35:12.631Z

Evaluation of Class Incremental Learning performance on the ImageNet-100 B0 subset configured for 10 sequential steps under a non-rehearsal protocol, reporting average and last accuracies.

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) | ImageNet100-B0 10 steps (non-rehearsal) |
| 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/class-incremental-learning-on-imagenet100-b0-10-steps-non-rehearsal.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

- [Last Step Accuracy](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet100-b0-10-steps-non-rehearsal.md?metric=Last%20Step%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TCIL | 84.05 | Not recorded | 68fa6e471e209131cea3ee78 |
| TCIL-Lite | 82.81 | Not recorded | 68fa6e471e209131cea3ee78 |
| WA | 65.52 | Not recorded | 68fa6e471e209131cea3ee78 |
| LwF-MC | 65.45 | Not recorded | 68fa6e471e209131cea3ee78 |
| BiC | 36.24 | Not recorded | 68fa6e471e209131cea3ee78 |
| DER | 29.15 | Not recorded | 68fa6e471e209131cea3ee78 |
| Finetuning | 28.48 | Not recorded | 68fa6e471e209131cea3ee78 |

### TCIL

Average Accuracy: 84.05. Result ID: 699022c73a6c314849fe5c86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3ee78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3ee78.md>)

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

Recorded evaluation configuration: {"#Paras":"64.1","Setting":"non-rehearsal"}. This record does not assert independent reproduction.

### TCIL-Lite

Average Accuracy: 82.81. Result ID: 699022c73a6c314849fe5c87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3ee78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3ee78.md>)

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

Recorded evaluation configuration: {"#Paras":"14.5","Setting":"non-rehearsal"}. This record does not assert independent reproduction.

### WA

Average Accuracy: 65.52. Result ID: 699022c73a6c314849fe5c84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3ee78.md>)

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

Recorded evaluation configuration: {"#Paras":"11.2","Setting":"non-rehearsal"}. This record does not assert independent reproduction.

### LwF-MC

Average Accuracy: 65.45. Result ID: 699022c73a6c314849fe5c82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3ee78.md>)

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

Recorded evaluation configuration: {"#Paras":"11.2","Setting":"non-rehearsal"}. This record does not assert independent reproduction.

### BiC

Average Accuracy: 36.24. Result ID: 699022c73a6c314849fe5c83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3ee78.md>)

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

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

Recorded evaluation configuration: {"#Paras":"11.2","Setting":"non-rehearsal"}. This record does not assert independent reproduction.

### DER

Average Accuracy: 29.15. Result ID: 699022c73a6c314849fe5c85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3ee78.md>)

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

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

Recorded evaluation configuration: {"#Paras":"61.6","Setting":"non-rehearsal"}. This record does not assert independent reproduction.

### Finetuning

Average Accuracy: 28.48. Result ID: 699022c73a6c314849fe5c81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3ee78.md>)

Recorded evaluation configuration: {"#Paras":"11.2","Setting":"non-rehearsal"}. This record does not assert independent reproduction.

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