# Image Classification on Waterbirds pixel space (test)

Source: [Image Classification on Waterbirds pixel space (test)](<https://www.sota2.com/research/sota/image-classification-on-waterbirds-pixel-space-test>)

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

Data updated: 2026-03-10T07:33:51.340Z

Evaluation of Image Classification performance on the test split of the Waterbirds dataset, specifically focusing on the 'pixel space' configuration, reporting average and worst-group accuracies.

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 | Image Classification |
| Dataset (including any stated split) | Waterbirds pixel space (test) |
| Metric | Average Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Average Accuracy](<https://www.sota2.com/research/sota/image-classification-on-waterbirds-pixel-space-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

- [Worst-Group Accuracy](<https://www.sota2.com/research/sota/image-classification-on-waterbirds-pixel-space-test.md?metric=Worst-Group%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Chroma-VAE | 70.46 | Not recorded | 6926896bd6b0dd3342930270 |
| JTT | 62.27 | Not recorded | 6926896bd6b0dd3342930270 |
| LfF | 57.76 | Not recorded | 6926896bd6b0dd3342930270 |
| SITAR | 57.13 | Not recorded | 6926896bd6b0dd3342930270 |
| ERM | 56.81 | Not recorded | 6926896bd6b0dd3342930270 |

### Chroma-VAE

Average Accuracy: 70.46. Result ID: 69afc9476dbb7075b957c94f.

[Reporting paper](<https://www.sota2.com/research/paper/6926896bd6b0dd3342930270.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e051e209131cea3d717.md>)

[Implementation](<https://github.com/Wanqianxn/chroma-vae-public>)

Recorded evaluation configuration: {"space":"pixel space","training\_condition":"without shortcut-conflicting samples (corr(Y, S) = 1)"}. This record does not assert independent reproduction.

### JTT

Average Accuracy: 62.27. Result ID: 69afc9476dbb7075b957c94d.

[Reporting paper](<https://www.sota2.com/research/paper/6926896bd6b0dd3342930270.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ade1e209131cea2aeeb.md>)

Recorded evaluation configuration: {"space":"pixel space","training\_condition":"without shortcut-conflicting samples (corr(Y, S) = 1)"}. This record does not assert independent reproduction.

### LfF

Average Accuracy: 57.76. Result ID: 69afc9476dbb7075b957c94e.

[Reporting paper](<https://www.sota2.com/research/paper/6926896bd6b0dd3342930270.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c11e209131cea1e11f.md>)

Recorded evaluation configuration: {"space":"pixel space","training\_condition":"without shortcut-conflicting samples (corr(Y, S) = 1)"}. This record does not assert independent reproduction.

### SITAR

Average Accuracy: 57.13. Result ID: 69afc9476dbb7075b957c950.

[Reporting paper](<https://www.sota2.com/research/paper/6926896bd6b0dd3342930270.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6926896bd6b0dd3342930270.md>)

Recorded evaluation configuration: {"space":"pixel space","training\_condition":"without shortcut-conflicting samples (corr(Y, S) = 1)"}. This record does not assert independent reproduction.

### ERM

Average Accuracy: 56.81. Result ID: 69afc9476dbb7075b957c94c.

[Reporting paper](<https://www.sota2.com/research/paper/6926896bd6b0dd3342930270.md>)

Recorded evaluation configuration: {"space":"pixel space","training\_condition":"without shortcut-conflicting samples (corr(Y, S) = 1)"}. This record does not assert independent reproduction.

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