# Federated Class-Incremental Learning on TinyImageNet first 10 tasks 35

Source: [Federated Class-Incremental Learning on TinyImageNet first 10 tasks 35](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35>)

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

Data updated: 2026-02-26T05:57:49.924Z

Evaluation of model performance using Federated Class-Incremental Learning methodology on the specific subset 'first 10 tasks 35' of the TinyImageNet dataset, reporting metrics across 10 learning stages.

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 | Federated Class-Incremental Learning |
| Dataset (including any stated split) | TinyImageNet first 10 tasks 35 |
| Metric | Performance @ 10% |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Performance @ 10%](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20%40%2010%25>): Higher is better; unit: PERCENT.

- [Performance @ 20%](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20%40%2020%25>): Higher is better; unit: PERCENT.

- [Performance @ 30%](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20%40%2030%25>): Higher is better; unit: PERCENT.

- [Performance @ 40%](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20%40%2040%25>): Higher is better; unit: PERCENT.

- [Performance @ 50%](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20%40%2050%25>): Higher is better; unit: PERCENT.

- [Performance @ 60%](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20%40%2060%25>): Higher is better; unit: PERCENT.

- [Performance @ 70%](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20%40%2070%25>): Higher is better; unit: PERCENT.

- [Performance @ 80%](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20%40%2080%25>): Higher is better; unit: PERCENT.

- [Performance @ 90%](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20%40%2090%25>): Higher is better; unit: PERCENT.

- [Performance @ 100%](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20%40%20100%25>): Higher is better; unit: PERCENT.

- [Average Performance](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Average%20Performance>): Higher is better; unit: PERCENT.

- [Performance Drop (Δ)](<https://www.sota2.com/research/sota/federated-class-incremental-learning-on-tinyimagenet-first-10-tasks-35.md?metric=Performance%20Drop%20(%CE%94)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Performance @ 10% | Result date | Report paper |
| --- | --- | --- | --- |
| DDE + iCaRL + FL | 70 | Not recorded | 68fa6c0d1e209131cea31b3c |
| PODNet + FL | 69 | Not recorded | 68fa6c0d1e209131cea31b3c |
| GLFC | 68.7 | Not recorded | 68fa6c0d1e209131cea31b3c |
| GLFC-w/oCRD | 68 | Not recorded | 68fa6c0d1e209131cea31b3c |
| GLFC-w/oCGC | 67.7 | Not recorded | 68fa6c0d1e209131cea31b3c |
| BiC + FL | 67.3 | Not recorded | 68fa6c0d1e209131cea31b3c |
| GLFC-w/oPRC | 67.3 | Not recorded | 68fa6c0d1e209131cea31b3c |
| iCaRL + FL | 67 | Not recorded | 68fa6c0d1e209131cea31b3c |
| SS-IL + FL | 66.7 | Not recorded | 68fa6c0d1e209131cea31b3c |
| GeoDL + iCaRL + FL | 66.3 | Not recorded | 68fa6c0d1e209131cea31b3c |

### DDE + iCaRL + FL

Performance @ 10%: 70. Result ID: 698ebd65ffc3901de0a03e27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa696f1e209131cea22081.md>)

[Implementation](<https://github.com/JoyHuYY1412/DDE_CIL>)

Recorded evaluation configuration: {"Incremental tasks":"20","Framework":"Federated Learning"}. This record does not assert independent reproduction.

### PODNet + FL

Performance @ 10%: 69. Result ID: 698ebd65ffc3901de0a03e26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.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: {"Incremental tasks":"20","Framework":"Federated Learning"}. This record does not assert independent reproduction.

### GLFC

Performance @ 10%: 68.7. Result ID: 698ebd65ffc3901de0a03e2d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Implementation](<https://github.com/conditionWang/FCIL>)

Recorded evaluation configuration: {"Incremental tasks":"20","Framework":"Federated Learning"}. This record does not assert independent reproduction.

### GLFC-w/oCRD

Performance @ 10%: 68. Result ID: 698ebd65ffc3901de0a03e2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Implementation](<https://github.com/conditionWang/FCIL>)

Recorded evaluation configuration: {"Incremental tasks":"20","Framework":"Federated Learning","Variant":"without CRD"}. This record does not assert independent reproduction.

### GLFC-w/oCGC

Performance @ 10%: 67.7. Result ID: 698ebd65ffc3901de0a03e2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Implementation](<https://github.com/conditionWang/FCIL>)

Recorded evaluation configuration: {"Incremental tasks":"20","Framework":"Federated Learning","Variant":"without CGC"}. This record does not assert independent reproduction.

### BiC + FL

Performance @ 10%: 67.3. Result ID: 698ebd65ffc3901de0a03e25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

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

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

Recorded evaluation configuration: {"Incremental tasks":"20","Framework":"Federated Learning"}. This record does not assert independent reproduction.

### GLFC-w/oPRC

Performance @ 10%: 67.3. Result ID: 698ebd65ffc3901de0a03e2c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Implementation](<https://github.com/conditionWang/FCIL>)

Recorded evaluation configuration: {"Incremental tasks":"20","Framework":"Federated Learning","Variant":"without PRC"}. This record does not assert independent reproduction.

### iCaRL + FL

Performance @ 10%: 67. Result ID: 698ebd65ffc3901de0a03e24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

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

Recorded evaluation configuration: {"Incremental tasks":"20","Framework":"Federated Learning"}. This record does not assert independent reproduction.

### SS-IL + FL

Performance @ 10%: 66.7. Result ID: 698ebd65ffc3901de0a03e29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd81e209131cea36380.md>)

Recorded evaluation configuration: {"Incremental tasks":"20","Framework":"Federated Learning"}. This record does not assert independent reproduction.

### GeoDL + iCaRL + FL

Performance @ 10%: 66.3. Result ID: 698ebd65ffc3901de0a03e28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ce1e209131cea243e5.md>)

[Implementation](<https://bit.ly/3adLNub>)

Recorded evaluation configuration: {"Incremental tasks":"20","Framework":"Federated Learning"}. This record does not assert independent reproduction.

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