# Image Classification on EMNIST Private Task Finetuned (test)

Source: [Image Classification on EMNIST Private Task Finetuned (test)](<https://www.sota2.com/research/sota/image-classification-on-emnist-private-task-finetuned-test>)

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

Data updated: 2026-03-05T08:07:41.853Z

Evaluation of Image Classification performance on the test split of the EMNIST Private Task Finetuned configuration.

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) | EMNIST Private Task Finetuned (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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-emnist-private-task-finetuned-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Quantum Augmentation Baseline | 85 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Gaussian Blur Augmented EMNIST Baseline | 80.7 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Gaussian Noise Augmented EMNIST Baseline | 11.4 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Gaussian Blur Augmented EMNIST Baseline | 6.1 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Public-Based Reward Policy | 4.6 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Length-Based Reward Policy | 4.3 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Accuracy-Based Reward Policy | 4.2 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Gaussian Noise Augmented EMNIST Baseline | 3.3 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Pure Chance Baseline | 2.8 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Accuracy-Based Reward Policy | 2.8 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Quantum Random Action Baseline | 2.7 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Public-Based Reward Policy | 2.5 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Length-Based Reward Policy | 2.4 | Not recorded | 68fa43ba1e209131ce90c1f0 |
| Quantum Random Action Baseline | 2.1 | Not recorded | 68fa43ba1e209131ce90c1f0 |

### Quantum Augmentation Baseline

Accuracy: 85. Result ID: 69a939956dbb7075b9527a41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

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

### Gaussian Blur Augmented EMNIST Baseline

Accuracy: 80.7. Result ID: 69a939956dbb7075b9527a45.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuned"}. This record does not assert independent reproduction.

### Gaussian Noise Augmented EMNIST Baseline

Accuracy: 11.4. Result ID: 69a939956dbb7075b9527a47.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuned"}. This record does not assert independent reproduction.

### Gaussian Blur Augmented EMNIST Baseline

Accuracy: 6.1. Result ID: 69a939956dbb7075b9527a44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Testing"}. This record does not assert independent reproduction.

### Public-Based Reward Policy

Accuracy: 4.6. Result ID: 69a939956dbb7075b9527a48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Testing","Training Steps":"90,397","Training Hours":"605"}. This record does not assert independent reproduction.

### Length-Based Reward Policy

Accuracy: 4.3. Result ID: 69a939956dbb7075b9527a4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuned","Training Steps":"28,519","Training Hours":"190"}. This record does not assert independent reproduction.

### Accuracy-Based Reward Policy

Accuracy: 4.2. Result ID: 69a939956dbb7075b9527a4c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Testing","Training Steps":"52,829","Training Hours":"348"}. This record does not assert independent reproduction.

### Gaussian Noise Augmented EMNIST Baseline

Accuracy: 3.3. Result ID: 69a939956dbb7075b9527a46.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Testing"}. This record does not assert independent reproduction.

### Pure Chance Baseline

Accuracy: 2.8. Result ID: 69a939956dbb7075b9527a40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

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

### Accuracy-Based Reward Policy

Accuracy: 2.8. Result ID: 69a939956dbb7075b9527a4d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuned","Training Steps":"52,829","Training Hours":"348"}. This record does not assert independent reproduction.

### Quantum Random Action Baseline

Accuracy: 2.7. Result ID: 69a939956dbb7075b9527a42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Testing"}. This record does not assert independent reproduction.

### Public-Based Reward Policy

Accuracy: 2.5. Result ID: 69a939956dbb7075b9527a49.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuned","Training Steps":"90,397","Training Hours":"605"}. This record does not assert independent reproduction.

### Length-Based Reward Policy

Accuracy: 2.4. Result ID: 69a939956dbb7075b9527a4a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Testing","Training Steps":"28,519","Training Hours":"190"}. This record does not assert independent reproduction.

### Quantum Random Action Baseline

Accuracy: 2.1. Result ID: 69a939956dbb7075b9527a43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa43ba1e209131ce90c1f0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuned"}. This record does not assert independent reproduction.

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