# Image Classification on SVHN → MNIST-LT (IF=20) (test)

Source: [Image Classification on SVHN → MNIST-LT (IF=20) (test)](<https://www.sota2.com/research/sota/image-classification-on-svhn-mnist-lt-if-20-test>)

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

Data updated: 2026-02-26T05:36:16.844Z

Evaluation of Image Classification performance on the test split of the MNIST dataset, using a Long-Tailed version of the SVHN dataset (Imbalance Factor 20) as the source domain for domain adaptation.

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) | SVHN → MNIST-LT (IF=20) (test) |
| Metric | Avg Per-Class 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

- [Avg Per-Class Accuracy](<https://www.sota2.com/research/sota/image-classification-on-svhn-mnist-lt-if-20-test.md?metric=Avg%20Per-Class%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg Per-Class Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SENTRY | 93.9 | Not recorded | 68fa6afc1e209131cea2b86e |
| InstaPBM | 77.9 | Not recorded | 68fa6afc1e209131cea2b86e |
| DANN | 71.5 | Not recorded | 68fa6afc1e209131cea2b86e |
| source | 68.1 | Not recorded | 68fa6afc1e209131cea2b86e |
| COAL | 67.1 | Not recorded | 68fa6afc1e209131cea2b86e |
| MMD | 56.7 | Not recorded | 68fa6afc1e209131cea2b86e |

### SENTRY

Avg Per-Class Accuracy: 93.9. Result ID: 698e4972ffc3901de09c549b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6afc1e209131cea2b86e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6afc1e209131cea2b86e.md>)

[Implementation](<https://github.com/virajprabhu/SENTRY>)

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

### InstaPBM

Avg Per-Class Accuracy: 77.9. Result ID: 698e4972ffc3901de09c549a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6afc1e209131cea2b86e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18aee.md>)

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

### DANN

Avg Per-Class Accuracy: 71.5. Result ID: 698e4972ffc3901de09c5498.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6afc1e209131cea2b86e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61b71e209131ce9f5a50.md>)

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

### source

Avg Per-Class Accuracy: 68.1. Result ID: 698e4972ffc3901de09c5496.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6afc1e209131cea2b86e.md>)

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

### COAL

Avg Per-Class Accuracy: 67.1. Result ID: 698e4972ffc3901de09c5499.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6afc1e209131cea2b86e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68671e209131cea1be3b.md>)

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

### MMD

Avg Per-Class Accuracy: 56.7. Result ID: 698e4972ffc3901de09c5497.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6afc1e209131cea2b86e.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.