# Class-conditional image synthesis on COCO-Animals 50k synthetic evaluation 128x128 (train test)

Source: [Class-conditional image synthesis on COCO-Animals 50k synthetic evaluation 128x128 (train test)](<https://www.sota2.com/research/sota/class-conditional-image-synthesis-on-coco-animals-50k-synthetic-evaluation-128x128-train-test>)

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

Data updated: 2026-02-26T05:44:12.357Z

Evaluation of Class-conditional image synthesis models using FID and Inception Score metrics on the synthetic COCO-Animals 50k dataset subset (128x128 resolution).

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 | Class-conditional image synthesis |
| Dataset (including any stated split) | COCO-Animals 50k synthetic evaluation 128x128 (train test) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower 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

- [FID](<https://www.sota2.com/research/sota/class-conditional-image-synthesis-on-coco-animals-50k-synthetic-evaluation-128x128-train-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [Best FID](<https://www.sota2.com/research/sota/class-conditional-image-synthesis-on-coco-animals-50k-synthetic-evaluation-128x128-train-test.md?metric=Best%20FID>): Lower is better; unit: SCALAR.

- [Best IS](<https://www.sota2.com/research/sota/class-conditional-image-synthesis-on-coco-animals-50k-synthetic-evaluation-128x128-train-test.md?metric=Best%20IS>): Higher is better; unit: SCALAR.

- [Median FID](<https://www.sota2.com/research/sota/class-conditional-image-synthesis-on-coco-animals-50k-synthetic-evaluation-128x128-train-test.md?metric=Median%20FID>): Lower is better; unit: SCALAR.

- [Median IS](<https://www.sota2.com/research/sota/class-conditional-image-synthesis-on-coco-animals-50k-synthetic-evaluation-128x128-train-test.md?metric=Median%20IS>): Higher is better; unit: SCALAR.

- [IS](<https://www.sota2.com/research/sota/class-conditional-image-synthesis-on-coco-animals-50k-synthetic-evaluation-128x128-train-test.md?metric=IS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| U-Net GAN | 13.73 | Not recorded | 68fa69971e209131cea22eac |
| U-Net GAN | 13.96 | Not recorded | 68fa69971e209131cea22eac |
| BigGAN | 16.37 | Not recorded | 68fa69971e209131cea22eac |
| BigGAN | 16.42 | Not recorded | 68fa69971e209131cea22eac |

### U-Net GAN

FID: 13.73. Result ID: 698dbd8f8b517eb43323715c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Implementation](<https://github.com/boschresearch/unetgan>)

Recorded evaluation configuration: {"Framework":"PyTorch","Resolution":"128x128","Training Iterations":"400k"}. This record does not assert independent reproduction.

### U-Net GAN

FID: 13.96. Result ID: 698dbd8f8b517eb43323715e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Implementation](<https://github.com/boschresearch/unetgan>)

Recorded evaluation configuration: {"Framework":"TensorFlow","Resolution":"128x128","Training Iterations":"400k"}. This record does not assert independent reproduction.

### BigGAN

FID: 16.37. Result ID: 698dbd8f8b517eb43323715b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65661e209131cea0a090.md>)

[Implementation](<https://tfhub.dev/s?q=biggan>)

Recorded evaluation configuration: {"Framework":"PyTorch","Resolution":"128x128","Training Iterations":"400k"}. This record does not assert independent reproduction.

### BigGAN

FID: 16.42. Result ID: 698dbd8f8b517eb43323715d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65661e209131cea0a090.md>)

[Implementation](<https://tfhub.dev/s?q=biggan>)

Recorded evaluation configuration: {"Framework":"TensorFlow","Resolution":"128x128","Training Iterations":"400k"}. This record does not assert independent reproduction.

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