# Handwritten Digit Classification on Superpixel MNIST 75 vertices (test)

Source: [Handwritten Digit Classification on Superpixel MNIST 75 vertices (test)](<https://www.sota2.com/research/sota/handwritten-digit-classification-on-superpixel-mnist-75-vertices-test>)

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

Data updated: 2026-02-26T05:28:18.156Z

Evaluation of handwritten digit classification performance on the test split of the Superpixel MNIST 75 vertices 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 | Handwritten digit classification |
| Dataset (including any stated split) | Superpixel MNIST 75 vertices (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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/handwritten-digit-classification-on-superpixel-mnist-75-vertices-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PolyConv | 0.9895 | Not recorded | 68fa6c881e209131cea34853 |
| PNCNN | 0.9876 | Not recorded | 68fa6c881e209131cea34853 |
| PolyConv | 0.9839 | Not recorded | 68fa6c881e209131cea34853 |
| GAT | 0.9619 | Not recorded | 68fa6c881e209131cea34853 |
| GCGP | 0.958 | Not recorded | 68fa6c881e209131cea34853 |
| SplineCNN | 0.9522 | Not recorded | 68fa6c881e209131cea34853 |
| MoNet | 0.9111 | Not recorded | 68fa6c881e209131cea34853 |

### PolyConv

Accuracy: 0.9895. Result ID: 698f20673a6c314849f60652.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea34853.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea34853.md>)

[Implementation](<https://www.sota2.com/this%20link>)

Recorded evaluation configuration: {"Complexity":"unsqueezed","Number of Parameters":"792k","Testing Time":"12.4 ms"}. This record does not assert independent reproduction.

### PNCNN

Accuracy: 0.9876. Result ID: 698f20673a6c314849f60650.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea34853.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68881e209131cea1cbd6.md>)

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

### PolyConv

Accuracy: 0.9839. Result ID: 698f20673a6c314849f60651.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea34853.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea34853.md>)

[Implementation](<https://www.sota2.com/this%20link>)

Recorded evaluation configuration: {"Complexity":"squeezed","Number of Parameters":"135k","Testing Time":"1.4 ms"}. This record does not assert independent reproduction.

### GAT

Accuracy: 0.9619. Result ID: 698f20673a6c314849f6064f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea34853.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68ba1e209131cea1dc9e.md>)

[Implementation](<https://github.com/machine-reasoning-ufrgs/spixel-gat>)

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

### GCGP

Accuracy: 0.958. Result ID: 698f20673a6c314849f6064e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea34853.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65bc1e209131cea0c047.md>)

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

### SplineCNN

Accuracy: 0.9522. Result ID: 698f20673a6c314849f6064d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea34853.md>)

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

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

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

### MoNet

Accuracy: 0.9111. Result ID: 698f20673a6c314849f6064c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea34853.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.