# Single-object Discovery on ImageNet 6 held-out classes (test) Source: [Single-object Discovery on ImageNet 6 held-out classes (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:09.666Z Evaluation of Single-object Discovery performance on the specific 6 held-out classes subset of the ImageNet dataset, measured using the Discovery metric. 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 | Single-object Discovery | | Dataset (including any stated split) | ImageNet 6 held-out classes (test) | | Metric | Discovery | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 2 of 2 | | 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 - [Discovery](): Higher is better; unit: PERCENT. ## Recorded results | Method | Discovery | Result date | Report paper | | --- | --- | --- | --- | | Wei et al. | 63.2 | Not recorded | 68fa68381e209131cea1ae0a | | Wei et al. | 61.2 | Not recorded | 68fa68381e209131cea1ae0a | ### Wei et al. Discovery: 63.2. Result ID: 698d64548b517eb43321296f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Features":"VGG19"}. This record does not assert independent reproduction. ### Wei et al. Discovery: 61.2. Result ID: 698d64548b517eb43321296e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Features":"VGG16"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.