# Digit Recognition on MNIST Rotated multiples of 15 domain M15 (test)

Source: [Digit Recognition on MNIST Rotated multiples of 15 domain M15 (test)](<https://www.sota2.com/research/sota/digit-recognition-on-mnist-rotated-multiples-of-15-domain-m15-test>)

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

Data updated: 2026-02-26T05:27:18.881Z

Evaluation of Digit Recognition performance on the specific test split of the MNIST Rotated dataset configured for multiples of 15 degrees (M15).

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 | Digit Recognition |
| Dataset (including any stated split) | MNIST Rotated multiples of 15 domain M15 (test) |
| Metric | 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

- [Accuracy](<https://www.sota2.com/research/sota/digit-recognition-on-mnist-rotated-multiples-of-15-domain-m15-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CROSSGRAD | 98.6 | Not recorded | 68fa644f1e209131cea03efd |
| DAN | 98 | Not recorded | 68fa644f1e209131cea03efd |
| LABELGRAD | 97.8 | Not recorded | 68fa644f1e209131cea03efd |
| Baseline (CCSA) | 95.6 | Not recorded | 68fa644f1e209131cea03efd |

### CROSSGRAD

Accuracy: 98.6. Result ID: 698c2c2c112aeb9460efef73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa644f1e209131cea03efd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa644f1e209131cea03efd.md>)

[Implementation](<https://github.com/vihari/crossgrad>)

Recorded evaluation configuration: {"Backbone":"2-layer convolutional network \[Motiian et al., 2017\]"}. This record does not assert independent reproduction.

### DAN

Accuracy: 98. Result ID: 698c2c2c112aeb9460efef71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa644f1e209131cea03efd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa627d1e209131ce9f988d.md>)

Recorded evaluation configuration: {"Backbone":"2-layer convolutional network \[Motiian et al., 2017\]"}. This record does not assert independent reproduction.

### LABELGRAD

Accuracy: 97.8. Result ID: 698c2c2c112aeb9460efef72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa644f1e209131cea03efd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61c91e209131ce9f5e06.md>)

Recorded evaluation configuration: {"Backbone":"2-layer convolutional network \[Motiian et al., 2017\]"}. This record does not assert independent reproduction.

### Baseline (CCSA)

Accuracy: 95.6. Result ID: 698c2c2c112aeb9460efef70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa644f1e209131cea03efd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63b81e209131cea00583.md>)

Recorded evaluation configuration: {"Backbone":"2-layer convolutional network \[Motiian et al., 2017\]"}. This record does not assert independent reproduction.

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