# Bird Classification on CUB-200-C

Source: [Bird Classification on CUB-200-C](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c>)

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

Data updated: 2026-04-20T08:35:59.501Z

Evaluation of Bird Classification performance on the CUB-200-C dataset, reporting accuracy across various corruption types including noise, blur, weather effects, and digital distortions.

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 | Bird Classification |
| Dataset (including any stated split) | CUB-200-C |
| Metric | Accuracy (Gauss Noise) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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 (Gauss Noise)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Gauss%20Noise)>): Higher is better; unit: PERCENT.

- [Accuracy (Shot Noise)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Shot%20Noise)>): Higher is better; unit: PERCENT.

- [Accuracy (Impulse Noise)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Impulse%20Noise)>): Higher is better; unit: PERCENT.

- [Accuracy (Speckle Noise)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Speckle%20Noise)>): Higher is better; unit: PERCENT.

- [Avg Accuracy (Noise)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Avg%20Accuracy%20(Noise)>): Higher is better; unit: PERCENT.

- [Accuracy (Defocus Blur)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Defocus%20Blur)>): Higher is better; unit: PERCENT.

- [Accuracy (Gauss Blur)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Gauss%20Blur)>): Higher is better; unit: PERCENT.

- [Avg Accuracy (Blur)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Avg%20Accuracy%20(Blur)>): Higher is better; unit: PERCENT.

- [Accuracy (Brightness Weather)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Brightness%20Weather)>): Higher is better; unit: PERCENT.

- [Accuracy (Fog Weather)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Fog%20Weather)>): Higher is better; unit: PERCENT.

- [Accuracy (Frost Weather)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Frost%20Weather)>): Higher is better; unit: PERCENT.

- [Avg Accuracy (Weather)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Avg%20Accuracy%20(Weather)>): Higher is better; unit: PERCENT.

- [Accuracy (Contrast Digital)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Contrast%20Digital)>): Higher is better; unit: PERCENT.

- [Accuracy (Elastic Digital)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Elastic%20Digital)>): Higher is better; unit: PERCENT.

- [Accuracy (JPEG Digital)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(JPEG%20Digital)>): Higher is better; unit: PERCENT.

- [Accuracy (Pixel Digital)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Accuracy%20(Pixel%20Digital)>): Higher is better; unit: PERCENT.

- [Avg Accuracy (Digital)](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Avg%20Accuracy%20(Digital)>): Higher is better; unit: PERCENT.

- [Overall Mean Accuracy](<https://www.sota2.com/research/sota/bird-classification-on-cub-200-c.md?metric=Overall%20Mean%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Gauss Noise) | Result date | Report paper |
| --- | --- | --- | --- |
| ProtoTTA | 52 | Not recorded | 69e5b30a7d0172140ec7df99 |
| EATA | 50.1 | Not recorded | 69e5b30a7d0172140ec7df99 |
| Tent | 45.8 | Not recorded | 69e5b30a7d0172140ec7df99 |
| SAR | 40 | Not recorded | 69e5b30a7d0172140ec7df99 |
| Unadapted | 37.3 | Not recorded | 69e5b30a7d0172140ec7df99 |
| Memo | 37.2 | Not recorded | 69e5b30a7d0172140ec7df99 |

### ProtoTTA

Accuracy (Gauss Noise): 52. Result ID: 69e5e56c47f34ce924cc1aa6.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

Recorded evaluation configuration: {"Backbone":"ProtoViT (LN)"}. This record does not assert independent reproduction.

### EATA

Accuracy (Gauss Noise): 50.1. Result ID: 69e5e56c47f34ce924cc1aa5.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea35123.md>)

Recorded evaluation configuration: {"Backbone":"ProtoViT (LN)"}. This record does not assert independent reproduction.

### Tent

Accuracy (Gauss Noise): 45.8. Result ID: 69e5e56c47f34ce924cc1aa4.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d2b.md>)

Recorded evaluation configuration: {"Backbone":"ProtoViT (LN)"}. This record does not assert independent reproduction.

### SAR

Accuracy (Gauss Noise): 40. Result ID: 69e5e56c47f34ce924cc1aa3.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e961e209131cea40e77.md>)

Recorded evaluation configuration: {"Backbone":"ProtoViT (LN)"}. This record does not assert independent reproduction.

### Unadapted

Accuracy (Gauss Noise): 37.3. Result ID: 69e5e56c47f34ce924cc1aa1.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

Recorded evaluation configuration: {"Backbone":"ProtoViT (LN)"}. This record does not assert independent reproduction.

### Memo

Accuracy (Gauss Noise): 37.2. Result ID: 69e5e56c47f34ce924cc1aa2.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da51e209131cea3b236.md>)

Recorded evaluation configuration: {"Backbone":"ProtoViT (LN)"}. This record does not assert independent reproduction.

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