# Image Classification on ImageNet (bACC, AUC, MCC, S/s, MB Report)

Source: [Image Classification on ImageNet (bACC, AUC, MCC, S/s, MB Report)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-bacc-auc-mcc-s-s-mb-report>)

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

Data updated: 2026-05-19T09:22:47.125Z

Evaluation of Image Classification performance on the standard ImageNet dataset, reporting a specific set of metrics including bACC, AUC, MCC, S/s, and MB.

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) | ImageNet |
| Metric | Balanced Accuracy (bACC) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Balanced Accuracy (bACC)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-bacc-auc-mcc-s-s-mb-report.md?metric=Balanced%20Accuracy%20(bACC)>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/image-classification-on-imagenet-bacc-auc-mcc-s-s-mb-report.md?metric=AUC>): Higher is better; unit: PERCENT.

- [MCC](<https://www.sota2.com/research/sota/image-classification-on-imagenet-bacc-auc-mcc-s-s-mb-report.md?metric=MCC>): Higher is better; unit: SCALAR.

- [Throughput (S/s)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-bacc-auc-mcc-s-s-mb-report.md?metric=Throughput%20(S%2Fs)>): Higher is better; unit: SCALAR.

- [Model Size (MB)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-bacc-auc-mcc-s-s-mb-report.md?metric=Model%20Size%20(MB)>): Lower is better; unit: SIZE.

## Recorded results

| Method | Balanced Accuracy (bACC) | Result date | Report paper |
| --- | --- | --- | --- |
| Latent Space Classifier + Distillation | 71.1 | Not recorded | 6a0beebfdbc836b87d82c611 |
| Latent Space Classifier | 63 | Not recorded | 6a0beebfdbc836b87d82c611 |
| Image Space Classifier | 45.9 | Not recorded | 6a0beebfdbc836b87d82c611 |

### Latent Space Classifier + Distillation

Balanced Accuracy (bACC): 71.1. Result ID: 6a0c2bd9fbc373592c0289b1.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beebfdbc836b87d82c611.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0beebfdbc836b87d82c611.md>)

Recorded evaluation configuration: {"Space":"+ Distill"}. This record does not assert independent reproduction.

### Latent Space Classifier

Balanced Accuracy (bACC): 63. Result ID: 6a0c2bd9fbc373592c0289b0.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beebfdbc836b87d82c611.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0beebfdbc836b87d82c611.md>)

Recorded evaluation configuration: {"Space":"Latent"}. This record does not assert independent reproduction.

### Image Space Classifier

Balanced Accuracy (bACC): 45.9. Result ID: 6a0c2bd9fbc373592c0289af.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beebfdbc836b87d82c611.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62321e209131ce9f8328.md>)

Recorded evaluation configuration: {"Space":"Image"}. This record does not assert independent reproduction.

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