# Outlier Detection on ImageNet-30 (10% Labeled + Unlabeled) Source: [Outlier Detection on ImageNet-30 (10% Labeled + Unlabeled)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:26:25.519Z Evaluation of Outlier Detection performance using a specific configuration of ImageNet-30 (10% labeled data and unlabeled data) as the in-distribution set, tested against various OOD datasets (LSUN, DTD, CUB, Flowers, Caltech, Dogs), reporting mean AUROC. 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 | Outlier Detection | | Dataset (including any stated split) | ImageNet-30 10% labeled data and unlabeled data | | Metric | AUROC (In-Distribution) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [AUROC (In-Distribution)](): Higher is better; unit: PERCENT. - [AUROC (LSUN)](): Higher is better; unit: PERCENT. - [AUROC (DTD)](): Higher is better; unit: PERCENT. - [AUROC (CUB)](): Higher is better; unit: PERCENT. - [AUROC (Flowers)](): Higher is better; unit: PERCENT. - [AUROC (Caltech)](): Higher is better; unit: PERCENT. - [AUROC (Dogs)](): Higher is better; unit: PERCENT. - [Mean AUROC (OOD)](): Higher is better; unit: PERCENT. ## Recorded results | Method | AUROC (In-Distribution) | Result date | Report paper | | --- | --- | --- | --- | | OpenMatch | 96.3 | Not recorded | 68fa6a951e209131cea290ea | | MTC | 93.8 | Not recorded | 68fa6a951e209131cea290ea | | Supervised | 92.8 | Not recorded | 68fa6a951e209131cea290ea | | FixMatch | 88.6 | Not recorded | 68fa6a951e209131cea290ea | | Labeled Only | 80.3 | Not recorded | 68fa6a951e209131cea290ea | ### OpenMatch AUROC (In-Distribution): 96.3. Result ID: 699ac18a5698665ec44fb577. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Supervision":"Semi-supervised","Labeled Data Ratio":"10%"}. This record does not assert independent reproduction. ### MTC AUROC (In-Distribution): 93.8. Result ID: 699ac18a5698665ec44fb576. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Supervision":"Semi-supervised","Labeled Data Ratio":"10%"}. This record does not assert independent reproduction. ### Supervised AUROC (In-Distribution): 92.8. Result ID: 699ac18a5698665ec44fb578. [Reporting paper]() Recorded evaluation configuration: {"Training Supervision":"Fully supervised","Training Condition":"Trained with fully labeled inliers"}. This record does not assert independent reproduction. ### FixMatch AUROC (In-Distribution): 88.6. Result ID: 699ac18a5698665ec44fb575. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Supervision":"Semi-supervised","Labeled Data Ratio":"10%"}. This record does not assert independent reproduction. ### Labeled Only AUROC (In-Distribution): 80.3. Result ID: 699ac18a5698665ec44fb574. [Reporting paper]() Recorded evaluation configuration: {"Training Supervision":"Semi-supervised","Labeled Data Ratio":"10%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.