# Hyperspectral Image Classification on Indian Pines 50/50 (test)

Source: [Hyperspectral Image Classification on Indian Pines 50/50 (test)](<https://www.sota2.com/research/sota/hyperspectral-image-classification-on-indian-pines-50-50-test>)

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

Data updated: 2026-05-28T09:42:13.315Z

Evaluation of hyperspectral image classification performance specifically on the 50/50 test split configuration of the Indian Pines dataset, typically reporting mean test 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 | Hyperspectral Image Classification |
| Dataset (including any stated split) | Indian Pines 50/50 (test) |
| Metric | Mean Test Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Mean Test Accuracy](<https://www.sota2.com/research/sota/hyperspectral-image-classification-on-indian-pines-50-50-test.md?metric=Mean%20Test%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Mean Test Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CP | 93.7 | Not recorded | 6a17cc46dbd7150506f814d0 |
| Tucker | 92.8 | Not recorded | 6a17cc46dbd7150506f814d0 |
| Scratch | 92.2 | Not recorded | 6a17cc46dbd7150506f814d0 |
| Reduce | 86.7 | Not recorded | 6a17cc46dbd7150506f814d0 |

### CP

Mean Test Accuracy: 93.7. Result ID: 6a180dd8fbc373592c1234cb.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc46dbd7150506f814d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc46dbd7150506f814d0.md>)

Recorded evaluation configuration: {"Model Type":"CP","Backbone":"DenseNet121","Rank (R)":"2","Number of trainable parameters":"27k"}. This record does not assert independent reproduction.

### Tucker

Mean Test Accuracy: 92.8. Result ID: 6a180dd8fbc373592c1234cc.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc46dbd7150506f814d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc46dbd7150506f814d0.md>)

Recorded evaluation configuration: {"Model Type":"Tucker","Backbone":"DenseNet121","Rank (R)":"2","Number of trainable parameters":"27k"}. This record does not assert independent reproduction.

### Scratch

Mean Test Accuracy: 92.2. Result ID: 6a180dd8fbc373592c1234ca.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc46dbd7150506f814d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69c81e209131cea23f34.md>)

[Implementation](<https://github.com/cogsys-tuebingen/deephs_fruit>)

Recorded evaluation configuration: {"Model Type":"Scratch","Backbone":"DenseNet121","Rank (R)":"2","Number of trainable parameters":"629k"}. This record does not assert independent reproduction.

### Reduce

Mean Test Accuracy: 86.7. Result ID: 6a180dd8fbc373592c1234c9.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc46dbd7150506f814d0.md>)

Recorded evaluation configuration: {"Model Type":"Reduce","Backbone":"DenseNet121","Rank (R)":"2","Number of trainable parameters":"27k"}. This record does not assert independent reproduction.

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