# Object Detection on MNIST-Hard (test)

Source: [Object Detection on MNIST-Hard (test)](<https://www.sota2.com/research/sota/object-detection-on-mnist-hard-test>)

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

Data updated: 2026-02-26T05:48:39.951Z

Evaluation of Object Detection performance (Localization and Classification) on the test split of the MNIST-Hard dataset variant.

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 | Object Detection |
| Dataset (including any stated split) | MNIST-Hard (test) |
| Metric | Localization Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Localization Accuracy](<https://www.sota2.com/research/sota/object-detection-on-mnist-hard-test.md?metric=Localization%20Accuracy>): Higher is better; unit: PERCENT.

- [Classification Accuracy](<https://www.sota2.com/research/sota/object-detection-on-mnist-hard-test.md?metric=Classification%20Accuracy>): Higher is better; unit: PERCENT.

- [Combined Accuracy (Loc & Classif)](<https://www.sota2.com/research/sota/object-detection-on-mnist-hard-test.md?metric=Combined%20Accuracy%20(Loc%20%26%20Classif)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Localization Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TUSK | 99.9 | Not recorded | 68fa6e591e209131cea3f3d7 |
| CNN | 99.6 | Not recorded | 68fa6e591e209131cea3f3d7 |
| MIST | 97.8 | Not recorded | 68fa6e591e209131cea3f3d7 |
| Xie et al. | 72.7 | Not recorded | 68fa6e591e209131cea3f3d7 |
| Ch.-wise | 25.4 | Not recorded | 68fa6e591e209131cea3f3d7 |

### TUSK

Localization Accuracy: 99.9. Result ID: 69902b533a6c314849fe9cff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e591e209131cea3f3d7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e591e209131cea3f3d7.md>)

Recorded evaluation configuration: {"Supervision level":"Unsupervised"}. This record does not assert independent reproduction.

### CNN

Localization Accuracy: 99.6. Result ID: 69902b533a6c314849fe9d03.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e591e209131cea3f3d7.md>)

Recorded evaluation configuration: {"Supervision level":"Fully Supervised"}. This record does not assert independent reproduction.

### MIST

Localization Accuracy: 97.8. Result ID: 69902b533a6c314849fe9d00.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e591e209131cea3f3d7.md>)

Recorded evaluation configuration: {"Supervision level":"Weakly Supervised"}. This record does not assert independent reproduction.

### Xie et al.

Localization Accuracy: 72.7. Result ID: 69902b533a6c314849fe9d01.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e591e209131cea3f3d7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671b1e209131cea14404.md>)

Recorded evaluation configuration: {"Supervision level":"Weakly Supervised"}. This record does not assert independent reproduction.

### Ch.-wise

Localization Accuracy: 25.4. Result ID: 69902b533a6c314849fe9d02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e591e209131cea3f3d7.md>)

Recorded evaluation configuration: {"Supervision level":"Weakly Supervised"}. This record does not assert independent reproduction.

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