# XAI Attribution Map Evaluation on ImageNet 1k mini (val)

Source: [XAI Attribution Map Evaluation on ImageNet 1k mini (val)](<https://www.sota2.com/research/sota/xai-attribution-map-evaluation-on-imagenet-1k-mini-val>)

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

Data updated: 2026-02-26T05:35:00.945Z

Evaluation of Explainable AI (XAI) attribution map fidelity on the validation split of the ImageNet 1k-mini dataset, measured using area, standard deviation, insertion, and deletion metrics.

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 Attribution Map Evaluation |
| Dataset (including any stated split) | ImageNet 1k mini (val) |
| Metric | Area Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Area Score](<https://www.sota2.com/research/sota/xai-attribution-map-evaluation-on-imagenet-1k-mini-val.md?metric=Area%20Score>): Higher is better; unit: SCALAR.

- [Std Dev](<https://www.sota2.com/research/sota/xai-attribution-map-evaluation-on-imagenet-1k-mini-val.md?metric=Std%20Dev>): Lower is better; unit: SCALAR.

- [Insertion Score](<https://www.sota2.com/research/sota/xai-attribution-map-evaluation-on-imagenet-1k-mini-val.md?metric=Insertion%20Score>): Higher is better; unit: SCALAR.

- [Deletion Score](<https://www.sota2.com/research/sota/xai-attribution-map-evaluation-on-imagenet-1k-mini-val.md?metric=Deletion%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Area Score | Result date | Report paper |
| --- | --- | --- | --- |
| KernelShap | 0.6686 | Not recorded | 68fa7a561e209131cea8293b |
| IG | 0.4063 | Not recorded | 68fa7a561e209131cea8293b |
| GradientShap | 0.2861 | Not recorded | 68fa7a561e209131cea8293b |
| LRP | 0.2749 | Not recorded | 68fa7a561e209131cea8293b |
| NoiseTunnel | 0.1847 | Not recorded | 68fa7a561e209131cea8293b |
| RISE | 0.1026 | Not recorded | 68fa7a561e209131cea8293b |
| LIME | 0.0649 | Not recorded | 68fa7a561e209131cea8293b |
| Grad-CAM | 0.0486 | Not recorded | 68fa7a561e209131cea8293b |
| rex | 0.0333 | Not recorded | 68fa7a561e209131cea8293b |

### KernelShap

Area Score: 0.6686. Result ID: 699ce3bc5698665ec48479ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8293b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d01e209131cea00e17.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### IG

Area Score: 0.4063. Result ID: 699ce3bc5698665ec48479ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8293b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63661e209131ce9fe6bd.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### GradientShap

Area Score: 0.2861. Result ID: 699ce3bc5698665ec48479ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8293b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d01e209131cea00e17.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### LRP

Area Score: 0.2749. Result ID: 699ce3bc5698665ec48479ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8293b.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### NoiseTunnel

Area Score: 0.1847. Result ID: 699ce3bc5698665ec48479eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8293b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63661e209131ce9fe6d2.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### RISE

Area Score: 0.1026. Result ID: 699ce3bc5698665ec48479f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8293b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64dc1e209131cea06cb9.md>)

[Implementation](<https://github.com/pytorch/vision>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### LIME

Area Score: 0.0649. Result ID: 699ce3bc5698665ec48479f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8293b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62a11e209131ce9fa620.md>)

[Implementation](<https://github.com/marcotcr/lime-experiments>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### Grad-CAM

Area Score: 0.0486. Result ID: 699ce3bc5698665ec48479ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8293b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68bd1e209131cea1dec5.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### rex

Area Score: 0.0333. Result ID: 699ce3bc5698665ec48479f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8293b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8293b.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

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