# Image Classification on Waterbirds (shifted)

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

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

Data updated: 2026-02-26T06:09:01.371Z

Evaluation of Image Classification performance on the shifted variant of the Waterbirds dataset, reporting group-aware metrics such as 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 (shifted) |
| Metric | Worst 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

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

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

## Recorded results

| Method | Worst Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Hierarchical Group DRO | 93.7 | Not recorded | 68fa7bd01e209131cea8aa30 |
| GroupDRO | 91.7 | Not recorded | 68fa7bd01e209131cea8aa30 |
| DFRtr | 89.2 | Not recorded | 68fa7bd01e209131cea8aa30 |
| PDE | 84.4 | Not recorded | 68fa7bd01e209131cea8aa30 |
| LISA | 79.1 | Not recorded | 68fa7bd01e209131cea8aa30 |

### Hierarchical Group DRO

Worst Accuracy: 93.7. Result ID: 699a3aa75698665ec4c10a39.

[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: 91.7. Result ID: 699a3aa75698665ec4c10a35.

[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.

### DFRtr

Worst Accuracy: 89.2. Result ID: 699a3aa75698665ec4c10a37.

[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.

### PDE

Worst Accuracy: 84.4. Result ID: 699a3aa75698665ec4c10a38.

[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.

### LISA

Worst Accuracy: 79.1. Result ID: 699a3aa75698665ec4c10a36.

[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.

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