# XAI Evaluation on ImageNet-S (test)

Source: [XAI Evaluation on ImageNet-S (test)](<https://www.sota2.com/research/sota/xai-evaluation-on-imagenet-s-test>)

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

Data updated: 2026-02-26T06:04:12.480Z

Evaluation of Explainable AI (XAI) methods, such as saliency map fidelity and localization metrics, performed specifically on the test split of the ImageNet-S dataset.

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 | XAI Evaluation |
| Dataset (including any stated split) | ImageNet-S (test) |
| Metric | Selectivity |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 0 of 0 |
| 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

- [Selectivity](<https://www.sota2.com/research/sota/xai-evaluation-on-imagenet-s-test.md?metric=Selectivity>): Higher is better; unit: SCALAR.

- [Attribution Localization](<https://www.sota2.com/research/sota/xai-evaluation-on-imagenet-s-test.md?metric=Attribution%20Localization>): Higher is better; unit: PERCENT.

- [Pointing Game](<https://www.sota2.com/research/sota/xai-evaluation-on-imagenet-s-test.md?metric=Pointing%20Game>): Higher is better; unit: SCALAR.

- [Pixel Flipping (AUC@5)](<https://www.sota2.com/research/sota/xai-evaluation-on-imagenet-s-test.md?metric=Pixel%20Flipping%20(AUC%405)>): Higher is better; unit: SCALAR.

- [Pixel Flipping (AUC@20)](<https://www.sota2.com/research/sota/xai-evaluation-on-imagenet-s-test.md?metric=Pixel%20Flipping%20(AUC%4020)>): Higher is better; unit: SCALAR.

- [Maximum Sensitivity](<https://www.sota2.com/research/sota/xai-evaluation-on-imagenet-s-test.md?metric=Maximum%20Sensitivity>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Selectivity | Result date | Report paper |
| --- | --- | --- | --- |

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