# Image Classification on Disjoint MNIST (test)

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

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

Data updated: 2026-02-26T05:27:57.242Z

Evaluation of Image Classification performance on the test split of the Disjoint MNIST 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) | Disjoint MNIST (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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-disjoint-mnist-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| OWM | 96.59 | Not recorded | 68fa6a3a1e209131cea26cbf |
| OWM | 96.3 | Not recorded | 68fa6a3a1e209131cea26cbf |
| CAB | 94.91 | Not recorded | 68fa6a3a1e209131cea26cbf |
| IMM | 94.12 | Not recorded | 68fa6a3a1e209131cea26cbf |
| SGD | 53.85 | Not recorded | 68fa6a3a1e209131cea26cbf |
| EWC | 52.72 | Not recorded | 68fa6a3a1e209131cea26cbf |

### OWM

Accuracy: 96.59. Result ID: 698e2034ffc3901de09afea4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3a1e209131cea26cbf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a3a1e209131cea26cbf.md>)

[Implementation](<https://github.com/beijixiong3510/OWM>)

Recorded evaluation configuration: {"Network Architecture":"4-layer network \[784-800-800-10\]"}. This record does not assert independent reproduction.

### OWM

Accuracy: 96.3. Result ID: 698e2034ffc3901de09afea7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3a1e209131cea26cbf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a3a1e209131cea26cbf.md>)

[Implementation](<https://github.com/beijixiong3510/OWM>)

Recorded evaluation configuration: {"Network Architecture":"3-layer network \[784-800-10\]"}. This record does not assert independent reproduction.

### CAB

Accuracy: 94.91. Result ID: 698e2034ffc3901de09afea6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3a1e209131cea26cbf.md>)

Recorded evaluation configuration: {"Network Architecture":"4-layer network \[784-2000-2000-10\]"}. This record does not assert independent reproduction.

### IMM

Accuracy: 94.12. Result ID: 698e2034ffc3901de09afea3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3a1e209131cea26cbf.md>)

Recorded evaluation configuration: {"Network Architecture":"4-layer network \[784-800-800-10\]"}. This record does not assert independent reproduction.

### SGD

Accuracy: 53.85. Result ID: 698e2034ffc3901de09afea5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3a1e209131cea26cbf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61b71e209131ce9f5b05.md>)

Recorded evaluation configuration: {"Network Architecture":"3-layer network \[784-800-10\]"}. This record does not assert independent reproduction.

### EWC

Accuracy: 52.72. Result ID: 698e2034ffc3901de09afea2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3a1e209131cea26cbf.md>)

Recorded evaluation configuration: {"Network Architecture":"4-layer network \[784-800-800-10\]"}. This record does not assert independent reproduction.

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