# Image Classification on MNIST Superpixels (75 nodes) (test)

Source: [Image Classification on MNIST Superpixels (75 nodes) (test)](<https://www.sota2.com/research/sota/image-classification-on-mnist-superpixels-75-nodes-test>)

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

Data updated: 2026-02-26T05:27:27.561Z

Evaluation of Image Classification performance on the test split of the MNIST Superpixels (75 nodes) 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 | Image classification |
| Dataset (including any stated split) | MNIST Superpixels (75 nodes) (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-mnist-superpixels-75-nodes-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Error Rate](<https://www.sota2.com/research/sota/image-classification-on-mnist-superpixels-75-nodes-test.md?metric=Error%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SplineCNN | 95.22 | Not recorded | 68fa64601e209131cea0425b |
| SplineCNN | 94.77 | Not recorded | 68fa64601e209131cea0425b |
| SplineCNN | 94.64 | Not recorded | 68fa64601e209131cea0425b |
| SplineCNN | 94.62 | Not recorded | 68fa64601e209131cea0425b |
| SplineCNN | 94.35 | Not recorded | 68fa64601e209131cea0425b |
| SplineCNN | 93.83 | Not recorded | 68fa64601e209131cea0425b |
| MoNet | 91.11 | Not recorded | 68fa64601e209131cea0425b |

### SplineCNN

Accuracy: 95.22. Result ID: 698c2e2f112aeb9460effe6b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Implementation](<https://github.com/rusty1s/pytorch_geometric>)

Recorded evaluation configuration: {"coordinates":"Cartesian","degree":"Linear"}. This record does not assert independent reproduction.

### SplineCNN

Accuracy: 94.77. Result ID: 698c2e2f112aeb9460effe6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Implementation](<https://github.com/rusty1s/pytorch_geometric>)

Recorded evaluation configuration: {"coordinates":"Cartesian","degree":"Quadratic"}. This record does not assert independent reproduction.

### SplineCNN

Accuracy: 94.64. Result ID: 698c2e2f112aeb9460effe6c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Implementation](<https://github.com/rusty1s/pytorch_geometric>)

Recorded evaluation configuration: {"coordinates":"Polar","degree":"Linear"}. This record does not assert independent reproduction.

### SplineCNN

Accuracy: 94.62. Result ID: 698c2e2f112aeb9460effe6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Implementation](<https://github.com/rusty1s/pytorch_geometric>)

Recorded evaluation configuration: {"coordinates":"Cartesian","degree":"Cubic"}. This record does not assert independent reproduction.

### SplineCNN

Accuracy: 94.35. Result ID: 698c2e2f112aeb9460effe6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Implementation](<https://github.com/rusty1s/pytorch_geometric>)

Recorded evaluation configuration: {"coordinates":"Polar","degree":"Quadratic"}. This record does not assert independent reproduction.

### SplineCNN

Accuracy: 93.83. Result ID: 698c2e2f112aeb9460effe70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Implementation](<https://github.com/rusty1s/pytorch_geometric>)

Recorded evaluation configuration: {"coordinates":"Polar","degree":"Cubic"}. This record does not assert independent reproduction.

### MoNet

Accuracy: 91.11. Result ID: 698c2e2f112aeb9460effe6a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64601e209131cea0425b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62fe1e209131ce9fc1dd.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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