# Few-Shot Class-Incremental Learning on CUB200 (10-way 5-shot setup)

Source: [Few-Shot Class-Incremental Learning on CUB200 (10-way 5-shot setup)](<https://www.sota2.com/research/sota/few-shot-class-incremental-learning-on-cub200-10-way-5-shot-setup>)

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

Data updated: 2026-02-26T05:37:37.428Z

Evaluation of Few-Shot Class-Incremental Learning performance on the CUB-200 dataset using a specific 10-way, 5-shot incremental learning protocol, reporting summary metrics like base, last, 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 | Few-Shot Class-Incremental Learning |
| Dataset (including any stated split) | CUB200 10-way 5-shot incremental setup |
| Metric | Base Acc |
| 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

- [Base Acc](<https://www.sota2.com/research/sota/few-shot-class-incremental-learning-on-cub200-10-way-5-shot-setup.md?metric=Base%20Acc>): Higher is better; unit: PERCENT.

- [Last Acc](<https://www.sota2.com/research/sota/few-shot-class-incremental-learning-on-cub200-10-way-5-shot-setup.md?metric=Last%20Acc>): Higher is better; unit: PERCENT.

- [Avg Acc](<https://www.sota2.com/research/sota/few-shot-class-incremental-learning-on-cub200-10-way-5-shot-setup.md?metric=Avg%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Base Acc | Result date | Report paper |
| --- | --- | --- | --- |
| Fine-Tuning + Proto | 84.21 | Not recorded | 68fa72b91e209131cea582a6 |
| PriViLege | 82.21 | Not recorded | 68fa72b91e209131cea582a6 |
| NC-FSCIL | 78.49 | Not recorded | 68fa72b91e209131cea582a6 |
| CEC | 75.4 | Not recorded | 68fa72b91e209131cea582a6 |
| WaRP | 67.74 | Not recorded | 68fa72b91e209131cea582a6 |
| DualPrompt | 53.37 | Not recorded | 68fa72b91e209131cea582a6 |
| L2P | 44.97 | Not recorded | 68fa72b91e209131cea582a6 |

### Fine-Tuning + Proto

Base Acc: 84.21. Result ID: 699255873a6c3148490e40a4.

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### PriViLege

Base Acc: 82.21. Result ID: 699255873a6c3148490e40aa.

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

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### NC-FSCIL

Base Acc: 78.49. Result ID: 699255873a6c3148490e40a8.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e801e209131cea405f0.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### CEC

Base Acc: 75.4. Result ID: 699255873a6c3148490e40a5.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa69af1e209131cea235e3.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### WaRP

Base Acc: 67.74. Result ID: 699255873a6c3148490e40a9.

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### DualPrompt

Base Acc: 53.37. Result ID: 699255873a6c3148490e40a7.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d341e209131cea38614.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### L2P

Base Acc: 44.97. Result ID: 699255873a6c3148490e40a6.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0c1e209131cea31ad7.md>)

[Implementation](<https://github.com/google-research/l2p>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

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