# Image Category Discovery on ImageNet 30-class subsets (test) Source: [Image Category Discovery on ImageNet 30-class subsets (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:20.091Z Evaluation of Image Category Discovery performance on a specific 30-class subset of the ImageNet dataset, typically measured using Accuracy (ACC) and Normalized Mutual Information (NMI). 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 Category Discovery | | Dataset (including any stated split) | ImageNet 30-class subsets (test) | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [Accuracy (100)](): Higher is better; unit: PERCENT. - [NMI](): Higher is better; unit: SCALAR. - [NMI (100)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | CCN-CCL | 74.4 | Not recorded | 68fa64871e209131cea0533d | | CCN-KCL | 73.8 | Not recorded | 68fa64871e209131cea0533d | | LSC | 73.3 | Not recorded | 68fa64871e209131cea0533d | | K-means | 71.9 | Not recorded | 68fa64871e209131cea0533d | | LPNMF | 43 | Not recorded | 68fa64871e209131cea0533d | ### CCN-CCL Accuracy: 74.4. Result ID: 698c4b1737894ef7d9cd4cd8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Pre-training":"ImageNet882 classification"}. This record does not assert independent reproduction. ### CCN-KCL Accuracy: 73.8. Result ID: 698c4b1737894ef7d9cd4cd7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Pre-training":"ImageNet882 classification"}. This record does not assert independent reproduction. ### LSC Accuracy: 73.3. Result ID: 698c4b1737894ef7d9cd4cd5. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Pre-training":"ImageNet882 classification"}. This record does not assert independent reproduction. ### K-means Accuracy: 71.9. Result ID: 698c4b1737894ef7d9cd4cd4. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Pre-training":"ImageNet882 classification"}. This record does not assert independent reproduction. ### LPNMF Accuracy: 43. Result ID: 698c4b1737894ef7d9cd4cd6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18","Pre-training":"ImageNet882 classification"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.