# Image Modeling on FMNIST

Source: [Image Modeling on FMNIST](<https://www.sota2.com/research/sota/image-modeling-on-fmnist>)

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

Data updated: 2026-02-26T05:44:13.916Z

Evaluation of generative model performance on the Fashion MNIST (FMNIST) dataset, measured using Fréchet Inception Distance (FID).

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 Modeling |
| Dataset (including any stated split) | FMNIST |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower 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

- [FID](<https://www.sota2.com/research/sota/image-modeling-on-fmnist.md?metric=FID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| RNFs-ML | 288.39 | Not recorded | 68fa6b281e209131cea2c660 |
| RNFs-ML | 296.01 | Not recorded | 68fa6b281e209131cea2c660 |
| RNFs-TS | 318.59 | Not recorded | 68fa6b281e209131cea2c660 |
| RNFs-ML | 342.91 | Not recorded | 68fa6b281e209131cea2c660 |

### RNFs-ML

FID: 288.39. Result ID: 698e61a9ffc3901de09d2039.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b281e209131cea2c660.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b281e209131cea2c660.md>)

[Implementation](<https://github.com/layer6ai-labs/rectangular-flows>)

Recorded evaluation configuration: {"K":1}. This record does not assert independent reproduction.

### RNFs-ML

FID: 296.01. Result ID: 698e61a9ffc3901de09d2038.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b281e209131cea2c660.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b281e209131cea2c660.md>)

[Implementation](<https://github.com/layer6ai-labs/rectangular-flows>)

Recorded evaluation configuration: {"variant":"exact"}. This record does not assert independent reproduction.

### RNFs-TS

FID: 318.59. Result ID: 698e61a9ffc3901de09d203b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b281e209131cea2c660.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b281e209131cea2c660.md>)

[Implementation](<https://github.com/layer6ai-labs/rectangular-flows>)

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

### RNFs-ML

FID: 342.91. Result ID: 698e61a9ffc3901de09d203a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b281e209131cea2c660.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b281e209131cea2c660.md>)

[Implementation](<https://github.com/layer6ai-labs/rectangular-flows>)

Recorded evaluation configuration: {"K":4}. This record does not assert independent reproduction.

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