# Image Classification on Waterbirds original unshifted

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

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

Data updated: 2026-02-26T06:09:01.422Z

Evaluation of Image Classification performance on the original, unshifted variant of the Waterbirds dataset, reporting Worst Accuracy 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 | Image Classification |
| Dataset (including any stated split) | Waterbirds original unshifted |
| Metric | Worst Accuracy |
| 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

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

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

## Recorded results

| Method | Worst Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Hierarchical Group DRO | 90.8 | Not recorded | 68fa7bd01e209131cea8aa30 |
| GroupDRO | 90.6 | Not recorded | 68fa7bd01e209131cea8aa30 |
| PDE | 90.3 | Not recorded | 68fa7bd01e209131cea8aa30 |
| DFRtr | 90.2 | Not recorded | 68fa7bd01e209131cea8aa30 |
| LISA | 89.2 | Not recorded | 68fa7bd01e209131cea8aa30 |
| SSA | 89 | Not recorded | 68fa7bd01e209131cea8aa30 |
| CnC | 88.5 | Not recorded | 68fa7bd01e209131cea8aa30 |
| GIC | 86.3 | Not recorded | 68fa7bd01e209131cea8aa30 |
| JTT | 83.8 | Not recorded | 68fa7bd01e209131cea8aa30 |
| ERM | 62.6 | Not recorded | 68fa7bd01e209131cea8aa30 |

### Hierarchical Group DRO

Worst Accuracy: 90.8. Result ID: 699a3aa75698665ec4c10a51.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

Recorded evaluation configuration: {"Group label":true}. This record does not assert independent reproduction.

### GroupDRO

Worst Accuracy: 90.6. Result ID: 699a3aa75698665ec4c10a4d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67561e209131cea159c7.md>)

Recorded evaluation configuration: {"Group label":true}. This record does not assert independent reproduction.

### PDE

Worst Accuracy: 90.3. Result ID: 699a3aa75698665ec4c10a50.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71021e209131cea4e848.md>)

Recorded evaluation configuration: {"Group label":true}. This record does not assert independent reproduction.

### DFRtr

Worst Accuracy: 90.2. Result ID: 699a3aa75698665ec4c10a4f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe41e209131cea47f22.md>)

Recorded evaluation configuration: {"Group label":true}. This record does not assert independent reproduction.

### LISA

Worst Accuracy: 89.2. Result ID: 699a3aa75698665ec4c10a4e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd91e209131cea36415.md>)

Recorded evaluation configuration: {"Group label":true}. This record does not assert independent reproduction.

### SSA

Worst Accuracy: 89. Result ID: 699a3aa75698665ec4c10a4c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2b1e209131cea3281e.md>)

Recorded evaluation configuration: {"Group label":false}. This record does not assert independent reproduction.

### CnC

Worst Accuracy: 88.5. Result ID: 699a3aa75698665ec4c10a4a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762d1e209131cea6bb11.md>)

Recorded evaluation configuration: {"Group label":false}. This record does not assert independent reproduction.

### GIC

Worst Accuracy: 86.3. Result ID: 699a3aa75698665ec4c10a4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73781e209131cea5cb95.md>)

Recorded evaluation configuration: {"Group label":false}. This record does not assert independent reproduction.

### JTT

Worst Accuracy: 83.8. Result ID: 699a3aa75698665ec4c10a49.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

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

Recorded evaluation configuration: {"Group label":false}. This record does not assert independent reproduction.

### ERM

Worst Accuracy: 62.6. Result ID: 699a3aa75698665ec4c10a48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa30.md>)

Recorded evaluation configuration: {"Group label":false}. This record does not assert independent reproduction.

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