# 50-shot 5-way Classification on miniImageNet (test) Source: [50-shot 5-way Classification on miniImageNet (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:42.911Z Evaluation of 50-shot, 5-way few-shot classification performance on the test split of the miniImageNet dataset, measured by 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 | 5-way 50-shot classification | | Dataset (including any stated split) | miniImageNet (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MAML | 75.54 | Not recorded | 68fa684f1e209131cea1b543 | | ProtoNets | 72.04 | Not recorded | 68fa684f1e209131cea1b543 | | CACTUs-MAML | 69.64 | Not recorded | 68fa684f1e209131cea1b543 | | ULDA-MetaOptNet | 67.65 | Not recorded | 68fa684f1e209131cea1b543 | | UMTRA | 67.15 | Not recorded | 68fa684f1e209131cea1b543 | | ULDA-ProtoNets | 66.43 | Not recorded | 68fa684f1e209131cea1b543 | | linear classifier | 65.28 | Not recorded | 68fa684f1e209131cea1b543 | | knn-nearest neighbors | 63.9 | Not recorded | 68fa684f1e209131cea1b543 | | CACTUs-ProtoNets | 63.55 | Not recorded | 68fa684f1e209131cea1b543 | | MLP with dropout | 60.95 | Not recorded | 68fa684f1e209131cea1b543 | | Training from scratch | 59.63 | Not recorded | 68fa684f1e209131cea1b543 | | cluster matching | 26.87 | Not recorded | 68fa684f1e209131cea1b543 | ### MAML Accuracy: 75.54. Result ID: 698d698d8b517eb433214d1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Clustering":"N/A","Training Protocol":"Supervised (Upper Bound)","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### ProtoNets Accuracy: 72.04. Result ID: 698d698d8b517eb433214d19. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Clustering":"N/A","Training Protocol":"Supervised (Upper Bound)","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### CACTUs-MAML Accuracy: 69.64. Result ID: 698d698d8b517eb433214d15. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Clustering":"DeepCluster","Training Protocol":"Unsupervised","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### ULDA-MetaOptNet Accuracy: 67.65. Result ID: 698d698d8b517eb433214d18. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Clustering":"N/A","Training Protocol":"Unsupervised","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### UMTRA Accuracy: 67.15. Result ID: 698d698d8b517eb433214d16. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Clustering":"N/A","Training Protocol":"Unsupervised","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### ULDA-ProtoNets Accuracy: 66.43. Result ID: 698d698d8b517eb433214d17. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Clustering":"N/A","Training Protocol":"Unsupervised","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### linear classifier Accuracy: 65.28. Result ID: 698d698d8b517eb433214d11. [Reporting paper]() Recorded evaluation configuration: {"Clustering":"DeepCluster","Training Protocol":"Unsupervised","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### knn-nearest neighbors Accuracy: 63.9. Result ID: 698d698d8b517eb433214d10. [Reporting paper]() Recorded evaluation configuration: {"Clustering":"DeepCluster","Training Protocol":"Unsupervised","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### CACTUs-ProtoNets Accuracy: 63.55. Result ID: 698d698d8b517eb433214d14. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Clustering":"DeepCluster","Training Protocol":"Unsupervised","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### MLP with dropout Accuracy: 60.95. Result ID: 698d698d8b517eb433214d12. [Reporting paper]() Recorded evaluation configuration: {"Clustering":"DeepCluster","Training Protocol":"Unsupervised","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### Training from scratch Accuracy: 59.63. Result ID: 698d698d8b517eb433214d0f. [Reporting paper]() Recorded evaluation configuration: {"Clustering":"N/A","Training Protocol":"Unsupervised","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. ### cluster matching Accuracy: 26.87. Result ID: 698d698d8b517eb433214d13. [Reporting paper]() Recorded evaluation configuration: {"Clustering":"DeepCluster","Training Protocol":"Unsupervised","Backbone":"4-layer CNN"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.