# Open-World Semi-Supervised Learning on ImageNet 100 (25/75 split)

Source: [Open-World Semi-Supervised Learning on ImageNet 100 (25/75 split)](<https://www.sota2.com/research/sota/open-world-semi-supervised-learning-on-imagenet-100-25-75-split>)

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

Data updated: 2026-02-26T06:04:09.941Z

Evaluation of Open-world Semi-supervised Learning performance on a specific 25/75 seen/novel split configuration of ImageNet-100, measured by Seen and Novel Accuracy.

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) | ImageNet 100 25/75 seen/novel split (unlabelled) |
| Metric | Seen Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Seen Accuracy](<https://www.sota2.com/research/sota/open-world-semi-supervised-learning-on-imagenet-100-25-75-split.md?metric=Seen%20Accuracy>): Higher is better; unit: PERCENT.

- [Novel Accuracy](<https://www.sota2.com/research/sota/open-world-semi-supervised-learning-on-imagenet-100-25-75-split.md?metric=Novel%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Seen Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Dual Ranking Statistics | 89.5 | Not recorded | 68fa6b881e209131cea2ee5a |
| ORCA | 89.4 | Not recorded | 68fa6b881e209131cea2ee5a |
| RankStat | 52.4 | Not recorded | 68fa6b881e209131cea2ee5a |
| DTC | 23.5 | Not recorded | 68fa6b881e209131cea2ee5a |

### Dual Ranking Statistics

Seen Accuracy: 89.5. Result ID: 698e94f6ffc3901de09ed8d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b881e209131cea2ee5a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b881e209131cea2ee5a.md>)

[Implementation](<https://github.com/DTennant/dual-rank-ncd>)

Recorded evaluation configuration: {"Split (seen/novel)":"25/75"}. This record does not assert independent reproduction.

### ORCA

Seen Accuracy: 89.4. Result ID: 698e94f6ffc3901de09ed8d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b881e209131cea2ee5a.md>)

Recorded evaluation configuration: {"Split (seen/novel)":"25/75"}. This record does not assert independent reproduction.

### RankStat

Seen Accuracy: 52.4. Result ID: 698e94f6ffc3901de09ed8d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b881e209131cea2ee5a.md>)

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

Recorded evaluation configuration: {"Split (seen/novel)":"25/75"}. This record does not assert independent reproduction.

### DTC

Seen Accuracy: 23.5. Result ID: 698e94f6ffc3901de09ed8d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b881e209131cea2ee5a.md>)

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

Recorded evaluation configuration: {"Split (seen/novel)":"25/75"}. This record does not assert independent reproduction.

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