# Image Classification on CIFAR-10 (Model Size and FLOPs)

Source: [Image Classification on CIFAR-10 (Model Size and FLOPs)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-model-size-and-flops>)

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

Data updated: 2026-05-11T09:00:18.882Z

Evaluation of Image Classification performance on CIFAR-10, reporting model size (parameters) and computational complexity (FLOPs).

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) | CIFAR-10 |
| Metric | Model Size (Params) |
| Unit | SIZE |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [Model Size (Params)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-model-size-and-flops.md?metric=Model%20Size%20(Params)>): Lower is better; unit: SIZE.

- [Total FLOPs](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-model-size-and-flops.md?metric=Total%20FLOPs>): Lower is better; unit: SIZE.

## Recorded results

| Method | Model Size (Params) | Result date | Report paper |
| --- | --- | --- | --- |
| Histogram Equaliz. | 0 | Not recorded | 6a016264dbc836b87d822f57 |
| Gamma (γ=2.2) | 0 | Not recorded | 6a016264dbc836b87d822f57 |
| GC-ART | 643 | Not recorded | 6a016264dbc836b87d822f57 |
| Zero-DCE++ | 1953 | Not recorded | 6a016264dbc836b87d822f57 |
| Zero-DCE | 11011 | Not recorded | 6a016264dbc836b87d822f57 |

### Histogram Equaliz.

Model Size (Params): 0. Result ID: 6a019a8c47f34ce924e3a0ef.

[Reporting paper](<https://www.sota2.com/research/paper/6a016264dbc836b87d822f57.md>)

Recorded evaluation configuration: {"Input Resolution":"32x32"}. This record does not assert independent reproduction.

### Gamma (γ=2.2)

Model Size (Params): 0. Result ID: 6a019a8c47f34ce924e3a0f0.

[Reporting paper](<https://www.sota2.com/research/paper/6a016264dbc836b87d822f57.md>)

Recorded evaluation configuration: {"gamma":"2.2","Input Resolution":"32x32"}. This record does not assert independent reproduction.

### GC-ART

Model Size (Params): 643. Result ID: 6a019a8c47f34ce924e3a0ec.

[Reporting paper](<https://www.sota2.com/research/paper/6a016264dbc836b87d822f57.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a016264dbc836b87d822f57.md>)

Recorded evaluation configuration: {"Input Resolution":"32x32"}. This record does not assert independent reproduction.

### Zero-DCE++

Model Size (Params): 1953. Result ID: 6a019a8c47f34ce924e3a0ee.

[Reporting paper](<https://www.sota2.com/research/paper/6a016264dbc836b87d822f57.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67421e209131cea15513.md>)

[Implementation](<https://li-chongyi.github.io/Proj_Zero-DCE.html/>)

Recorded evaluation configuration: {"Input Resolution":"32x32"}. This record does not assert independent reproduction.

### Zero-DCE

Model Size (Params): 11011. Result ID: 6a019a8c47f34ce924e3a0ed.

[Reporting paper](<https://www.sota2.com/research/paper/6a016264dbc836b87d822f57.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67421e209131cea15513.md>)

[Implementation](<https://li-chongyi.github.io/Proj_Zero-DCE.html/>)

Recorded evaluation configuration: {"Input Resolution":"32x32"}. This record does not assert independent reproduction.

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