# Class-Incremental Learning on ImageNet-1000 100-100 scenario

Source: [Class-Incremental Learning on ImageNet-1000 100-100 scenario](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-1000-100-100-scenario>)

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

Data updated: 2026-03-11T07:13:57.806Z

Evaluation of Class-Incremental Learning performance on the ImageNet-1000 dataset configured under the specific 100-100 scenario setup, reporting Last Accuracy 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-1000 100-100 scenario |
| Metric | Last Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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-1000-100-100-scenario.md?metric=Last%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-1000-100-100-scenario.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Last Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TagFex w/ CPNS | 62.44 | Not recorded | 69b0f6fb2d603e6de3e45cd5 |
| TagFex | 61.45 | Not recorded | 69b0f6fb2d603e6de3e45cd5 |
| TagFex-P w/ CPNS | 61.02 | Not recorded | 69b0f6fb2d603e6de3e45cd5 |
| DER w/ CPNS | 60.25 | Not recorded | 69b0f6fb2d603e6de3e45cd5 |
| TagFex-P | 60.14 | Not recorded | 69b0f6fb2d603e6de3e45cd5 |
| FOSTER w/ CPNS | 60.12 | Not recorded | 69b0f6fb2d603e6de3e45cd5 |
| FOSTER | 59.03 | Not recorded | 69b0f6fb2d603e6de3e45cd5 |
| DER | 58.83 | Not recorded | 69b0f6fb2d603e6de3e45cd5 |

### TagFex w/ CPNS

Last Accuracy: 62.44. Result ID: 69b1161c6dbb7075b95b09c3.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

Recorded evaluation configuration: {"Scenario":"100-100"}. This record does not assert independent reproduction.

### TagFex

Last Accuracy: 61.45. Result ID: 69b1161c6dbb7075b95b09c2.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77371e209131cea71afc.md>)

[Implementation](<https://github.com/bwnzheng/TagFex_CVPR2025>)

Recorded evaluation configuration: {"Scenario":"100-100"}. This record does not assert independent reproduction.

### TagFex-P w/ CPNS

Last Accuracy: 61.02. Result ID: 69b1161c6dbb7075b95b09c1.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

Recorded evaluation configuration: {"Scenario":"100-100"}. This record does not assert independent reproduction.

### DER w/ CPNS

Last Accuracy: 60.25. Result ID: 69b1161c6dbb7075b95b09bd.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

Recorded evaluation configuration: {"Scenario":"100-100"}. This record does not assert independent reproduction.

### TagFex-P

Last Accuracy: 60.14. Result ID: 69b1161c6dbb7075b95b09c0.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa660e1e209131cea0ded0.md>)

Recorded evaluation configuration: {"Scenario":"100-100"}. This record does not assert independent reproduction.

### FOSTER w/ CPNS

Last Accuracy: 60.12. Result ID: 69b1161c6dbb7075b95b09bf.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

Recorded evaluation configuration: {"Scenario":"100-100"}. This record does not assert independent reproduction.

### FOSTER

Last Accuracy: 59.03. Result ID: 69b1161c6dbb7075b95b09be.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

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

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

Recorded evaluation configuration: {"Scenario":"100-100"}. This record does not assert independent reproduction.

### DER

Last Accuracy: 58.83. Result ID: 69b1161c6dbb7075b95b09bc.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fb2d603e6de3e45cd5.md>)

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

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

Recorded evaluation configuration: {"Scenario":"100-100"}. This record does not assert independent reproduction.

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