# Image Classification on WebVision mini

Source: [Image Classification on WebVision mini](<https://www.sota2.com/research/sota/image-classification-on-webvision-mini>)

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

Data updated: 2026-02-26T05:28:23.505Z

Evaluation of Image Classification performance on the WebVision mini dataset.

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) | WebVision mini |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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-webvision-mini.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| NCR+Mixup+DA | 80.5 | Not recorded | 68fa6cf91e209131cea37049 |
| NCR+Mixup | 79.4 | Not recorded | 68fa6cf91e209131cea37049 |
| GJS | 79.3 | Not recorded | 68fa6cf91e209131cea37049 |
| ELR+ | 77.8 | Not recorded | 68fa6cf91e209131cea37049 |
| Mixup | 77.2 | Not recorded | 68fa6cf91e209131cea37049 |
| NCR | 77.1 | Not recorded | 68fa6cf91e209131cea37049 |
| ELR | 76.3 | Not recorded | 68fa6cf91e209131cea37049 |
| DMix | 76.3 | Not recorded | 68fa6cf91e209131cea37049 |
| Standard | 75.8 | Not recorded | 68fa6cf91e209131cea37049 |

### NCR+Mixup+DA

Accuracy: 80.5. Result ID: 698f6fdd3a6c314849f88f73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Implementation](<https://github.com/google-research/scenic/tree/main/scenic/projects/ncr>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### NCR+Mixup

Accuracy: 79.4. Result ID: 698f6fdd3a6c314849f88f72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Implementation](<https://github.com/google-research/scenic/tree/main/scenic/projects/ncr>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### GJS

Accuracy: 79.3. Result ID: 698f6fdd3a6c314849f88f77.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8b8.md>)

[Implementation](<https://github.com/ErikEnglesson/GJS>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### ELR+

Accuracy: 77.8. Result ID: 698f6fdd3a6c314849f88f75.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d383.md>)

[Implementation](<https://github.com/shengliu66/ELR>)

Recorded evaluation configuration: {"Backbone":"Inception-ResNetV2"}. This record does not assert independent reproduction.

### Mixup

Accuracy: 77.2. Result ID: 698f6fdd3a6c314849f88f70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa644e1e209131cea03e44.md>)

[Implementation](<https://github.com/facebookresearch/mixup-cifar10>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### NCR

Accuracy: 77.1. Result ID: 698f6fdd3a6c314849f88f71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Implementation](<https://github.com/google-research/scenic/tree/main/scenic/projects/ncr>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### ELR

Accuracy: 76.3. Result ID: 698f6fdd3a6c314849f88f74.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d383.md>)

[Implementation](<https://github.com/shengliu66/ELR>)

Recorded evaluation configuration: {"Backbone":"Inception-ResNetV2"}. This record does not assert independent reproduction.

### DMix

Accuracy: 76.3. Result ID: 698f6fdd3a6c314849f88f76.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671c1e209131cea144cf.md>)

[Implementation](<https://github.com/LiJunnan1992/DivideMix>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### Standard

Accuracy: 75.8. Result ID: 698f6fdd3a6c314849f88f6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf91e209131cea37049.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

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