# Image Classification on CIFAR-10 (test) (Seen/Unseen Metrics)

Source: [Image Classification on CIFAR-10 (test) (Seen/Unseen Metrics)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-seen-unseen-metrics>)

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

Data updated: 2026-04-03T09:20:23.465Z

Evaluation of Image Classification model performance on the CIFAR-10 test set, reporting metrics specifically categorized as 'Seen' and 'Unseen' performance indicators, likely related to generalization or out-of-distribution testing.

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 (test) |
| Metric | Accuracy (Seen) |
| 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

- [Accuracy (Seen)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-seen-unseen-metrics.md?metric=Accuracy%20(Seen)>): Higher is better; unit: PERCENT.

- [Accuracy (Unseen)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-seen-unseen-metrics.md?metric=Accuracy%20(Unseen)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Seen) | Result date | Report paper |
| --- | --- | --- | --- |
| UHN | 91.45 | Not recorded | 69cf49c20636e5bf4afcdc37 |
| UHN | 90.38 | Not recorded | 69cf49c20636e5bf4afcdc37 |
| UHN | 88.42 | Not recorded | 69cf49c20636e5bf4afcdc37 |

### UHN

Accuracy (Seen): 91.45. Result ID: 69cf865347f34ce924b9ae5e.

[Reporting paper](<https://www.sota2.com/research/paper/69cf49c20636e5bf4afcdc37.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cf49c20636e5bf4afcdc37.md>)

Recorded evaluation configuration: {"Model family":"CNN Mixed Width","#Models":"500","Avg. #Params":"624,987","Max #Params":"1,072,586","UHN #Params":"663,151"}. This record does not assert independent reproduction.

### UHN

Accuracy (Seen): 90.38. Result ID: 69cf865347f34ce924b9ae5f.

[Reporting paper](<https://www.sota2.com/research/paper/69cf49c20636e5bf4afcdc37.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cf49c20636e5bf4afcdc37.md>)

Recorded evaluation configuration: {"Model family":"CNN Mixed Depth × Width","#Models":"1000","Avg. #Params":"734,206","Max #Params":"1,372,110","UHN #Params":"663,151"}. This record does not assert independent reproduction.

### UHN

Accuracy (Seen): 88.42. Result ID: 69cf865347f34ce924b9ae5d.

[Reporting paper](<https://www.sota2.com/research/paper/69cf49c20636e5bf4afcdc37.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cf49c20636e5bf4afcdc37.md>)

Recorded evaluation configuration: {"Model family":"CNN Mixed Depth","#Models":"100","Avg. #Params":"366,995","Max #Params":"463,018","UHN #Params":"663,151"}. This record does not assert independent reproduction.

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