# Few-Shot Class-Incremental Learning on MiniImageNet (Base and Last Session)

Source: [Few-Shot Class-Incremental Learning on MiniImageNet (Base and Last Session)](<https://www.sota2.com/research/sota/few-shot-class-incremental-learning-on-miniimagenet-base-and-last-session>)

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

Data updated: 2026-02-26T05:34:10.137Z

Evaluation of Few-Shot Class-Incremental Learning performance on the MiniImageNet dataset, specifically reporting accuracy metrics for the initial base training session and the final session results.

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 | Few-Shot Class-Incremental Learning |
| Dataset (including any stated split) | MiniImageNet (base and last session) |
| Metric | Accuracy (Base Session) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Accuracy (Base Session)](<https://www.sota2.com/research/sota/few-shot-class-incremental-learning-on-miniimagenet-base-and-last-session.md?metric=Accuracy%20(Base%20Session)>): Higher is better; unit: PERCENT.

- [Accuracy (Last Session)](<https://www.sota2.com/research/sota/few-shot-class-incremental-learning-on-miniimagenet-base-and-last-session.md?metric=Accuracy%20(Last%20Session)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Base Session) | Result date | Report paper |
| --- | --- | --- | --- |
| PriViLege | 96.68 | Not recorded | 6965d1b06343fa78c83238d5 |
| LIMIT+SV | 90.55 | Not recorded | 6965d1b06343fa78c83238d5 |
| CPE-CLIP | 90.23 | Not recorded | 6965d1b06343fa78c83238d5 |
| GCMR | 87.38 | Not recorded | 6965d1b06343fa78c83238d5 |

### PriViLege

Accuracy (Base Session): 96.68. Result ID: 6997cc4a5698665ec423806e.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b06343fa78c83238d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b91e209131cea582a6.md>)

[Implementation](<https://github.com/KHU-AGI/PriViLege>)

Recorded evaluation configuration: {"Pretraining":"Large model pretraining"}. This record does not assert independent reproduction.

### LIMIT+SV

Accuracy (Base Session): 90.55. Result ID: 6997cc4a5698665ec423806c.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b06343fa78c83238d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428f2.md>)

Recorded evaluation configuration: {"Pretraining":"Large model pretraining"}. This record does not assert independent reproduction.

### CPE-CLIP

Accuracy (Base Session): 90.23. Result ID: 6997cc4a5698665ec423806d.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b06343fa78c83238d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d11e209131cea53203.md>)

Recorded evaluation configuration: {"Pretraining":"Large model pretraining"}. This record does not assert independent reproduction.

### GCMR

Accuracy (Base Session): 87.38. Result ID: 6997cc4a5698665ec423806b.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1b06343fa78c83238d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6965d1b06343fa78c83238d5.md>)

Recorded evaluation configuration: {"Pretraining":"Large model pretraining"}. This record does not assert independent reproduction.

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