# Neuron Explanation on MS COCO subset of 24,237 images 2017 (train)

Source: [Neuron Explanation on MS COCO subset of 24,237 images 2017 (train)](<https://www.sota2.com/research/sota/neuron-explanation-on-ms-coco-subset-of-24-237-images-2017-train>)

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

Data updated: 2026-02-26T05:42:37.569Z

Evaluation of Neuron Explanation performance using Explanation Accuracy on a specific subset of the MS COCO 2017 training data.

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 | Neuron Explanation |
| Dataset (including any stated split) | MS COCO subset of 24,237 images 2017 (train) |
| Metric | Explanation Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Explanation Accuracy](<https://www.sota2.com/research/sota/neuron-explanation-on-ms-coco-subset-of-24-237-images-2017-train.md?metric=Explanation%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Explanation Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| INVERT | 98.77 | Not recorded | 68fa71e11e209131cea53854 |
| NetDissect | 95.06 | Not recorded | 68fa71e11e209131cea53854 |

### INVERT

Explanation Accuracy: 98.77. Result ID: 6991ff7f3a6c3148490bf165.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71e11e209131cea53854.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71e11e209131cea53854.md>)

[Implementation](<https://github.com/lapalap/invert>)

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

### NetDissect

Explanation Accuracy: 95.06. Result ID: 6991ff7f3a6c3148490bf164.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71e11e209131cea53854.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634f1e209131ce9fdffb.md>)

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

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