# Open-world Semi-Supervised Learning on CIFAR-10 (50% known, 50% novel split)

Source: [Open-world Semi-Supervised Learning on CIFAR-10 (50% known, 50% novel split)](<https://www.sota2.com/research/sota/open-world-semi-supervised-learning-on-cifar-10-50-percent-known-50-percent-novel-split>)

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

Data updated: 2026-02-26T05:47:55.564Z

Evaluation of Open-world Semi-Supervised Learning performance on CIFAR-10, utilizing a specific experimental setup where 50% of classes are designated as known and 50% as novel during training/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 | Open-world Semi-Supervised Learning |
| Dataset (including any stated split) | CIFAR-10 50% known, 50% novel |
| Metric | Known 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

- [Known Accuracy](<https://www.sota2.com/research/sota/open-world-semi-supervised-learning-on-cifar-10-50-percent-known-50-percent-novel-split.md?metric=Known%20Accuracy>): Higher is better; unit: PERCENT.

- [Novel Accuracy](<https://www.sota2.com/research/sota/open-world-semi-supervised-learning-on-cifar-10-50-percent-known-50-percent-novel-split.md?metric=Novel%20Accuracy>): Higher is better; unit: PERCENT.

- [Overall Accuracy](<https://www.sota2.com/research/sota/open-world-semi-supervised-learning-on-cifar-10-50-percent-known-50-percent-novel-split.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Known Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| OpenLDN | 95.7 | Not recorded | 68fa6d201e209131cea37fab |
| OpenLDN | 95.2 | Not recorded | 68fa6d201e209131cea37fab |
| UNO | 91.6 | Not recorded | 68fa6d201e209131cea37fab |
| ORCA | 88.2 | Not recorded | 68fa6d201e209131cea37fab |
| RankStats | 86.6 | Not recorded | 68fa6d201e209131cea37fab |
| DS3L | 77.6 | Not recorded | 68fa6d201e209131cea37fab |
| CGDL | 72.3 | Not recorded | 68fa6d201e209131cea37fab |
| FixMatch | 71.5 | Not recorded | 68fa6d201e209131cea37fab |
| DTC | 53.9 | Not recorded | 68fa6d201e209131cea37fab |

### OpenLDN

Known Accuracy: 95.7. Result ID: 698f801b3a6c314849f9542e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

[Implementation](<https://github.com/nayeemrizve/OpenLDN>)

Recorded evaluation configuration: {"SSL Framework":"UDA"}. This record does not assert independent reproduction.

### OpenLDN

Known Accuracy: 95.2. Result ID: 698f801b3a6c314849f9542d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

[Implementation](<https://github.com/nayeemrizve/OpenLDN>)

Recorded evaluation configuration: {"SSL Framework":"MixMatch"}. This record does not assert independent reproduction.

### UNO

Known Accuracy: 91.6. Result ID: 698f801b3a6c314849f9542b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ae91e209131cea2afa3.md>)

[Implementation](<https://ncd-uno.github.io/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ORCA

Known Accuracy: 88.2. Result ID: 698f801b3a6c314849f9542c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ba21e209131cea2f704.md>)

[Implementation](<https://github.com/snap-stanford/orca>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RankStats

Known Accuracy: 86.6. Result ID: 698f801b3a6c314849f9542a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67091e209131cea14026.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DS3L

Known Accuracy: 77.6. Result ID: 698f801b3a6c314849f95427.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CGDL

Known Accuracy: 72.3. Result ID: 698f801b3a6c314849f95428.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69361e209131cea20d98.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FixMatch

Known Accuracy: 71.5. Result ID: 698f801b3a6c314849f95426.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d61e209131cea1e896.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DTC

Known Accuracy: 53.9. Result ID: 698f801b3a6c314849f95429.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d201e209131cea37fab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66441e209131cea0f56d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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