# Few-shot classification on MiniImageNet 5-Shot 5-Way (test) Source: [Few-shot classification on MiniImageNet 5-Shot 5-Way (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:02.699Z Evaluation of 5-shot, 5-way few-shot classification performance on the test split of the MiniImageNet dataset. 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 | Few-shot classification | | Dataset (including any stated split) | MiniImageNet 5-Shot 5-Way (test) | | Metric | Accuracy | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | FEAT | 0.8205 | Not recorded | 68fa6a211e209131cea262a3 | | GCN | 0.8165 | Not recorded | 68fa6a211e209131cea262a3 | | DEEPSETS | 0.8093 | Not recorded | 68fa6a211e209131cea262a3 | | BILSTM | 0.8062 | Not recorded | 68fa6a211e209131cea262a3 | | ProtoNet | 0.8053 | Not recorded | 68fa6a211e209131cea262a3 | | CTM | 0.8051 | Not recorded | 68fa6a211e209131cea262a3 | | SimpleShot | 0.8002 | Not recorded | 68fa6a211e209131cea262a3 | | MetaOptNet | 0.7863 | Not recorded | 68fa6a211e209131cea262a3 | | TADAM | 0.767 | Not recorded | 68fa6a211e209131cea262a3 | | PFA | 0.7374 | Not recorded | 68fa6a211e209131cea262a3 | | sparse-ReLU-MAML | 0.7301 | Not recorded | 68fa6b171e209131cea2c19f | | FEAT | 0.7161 | Not recorded | 68fa6a211e209131cea262a3 | | ProtoNet | 0.7133 | Not recorded | 68fa6a211e209131cea262a3 | | DEEPSETS | 0.7096 | Not recorded | 68fa6a211e209131cea262a3 | | MetaOptNet | 0.7088 | Not recorded | 68fa6b171e209131cea2c19f | | GCN | 0.7059 | Not recorded | 68fa6a211e209131cea262a3 | | BOIL | 0.705 | Not recorded | 68fa6b171e209131cea2c19f | | ANIL | 0.7003 | Not recorded | 68fa6b171e209131cea2c19f | | sparse-MAML | 0.7002 | Not recorded | 68fa6b171e209131cea2c19f | | MAML | 0.6936 | Not recorded | 68fa6b171e209131cea2c19f | | BILSTM | 0.6915 | Not recorded | 68fa6a211e209131cea262a3 | | ProtoNet | 0.682 | Not recorded | 68fa6a211e209131cea262a3 | | PFA | 0.6787 | Not recorded | 68fa6a211e209131cea262a3 | | RelationNet | 0.6707 | Not recorded | 68fa6a211e209131cea262a3 | | SimpleShot | 0.6692 | Not recorded | 68fa6a211e209131cea262a3 | | MAML | 0.6311 | Not recorded | 68fa6a211e209131cea262a3 | | MatchNet | 0.5109 | Not recorded | 68fa6a211e209131cea262a3 | ### FEAT Accuracy: 0.8205. Result ID: 698e12b0ffc3901de09a942a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Setup":"Embedding adaptation","Backbone":"ResNet"}. This record does not assert independent reproduction. ### GCN Accuracy: 0.8165. Result ID: 698e12b0ffc3901de09a9428. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Setup":"Embedding adaptation","Backbone":"ResNet"}. This record does not assert independent reproduction. ### DEEPSETS Accuracy: 0.8093. Result ID: 698e12b0ffc3901de09a9426. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"Embedding adaptation","Backbone":"ResNet"}. This record does not assert independent reproduction. ### BILSTM Accuracy: 0.8062. Result ID: 698e12b0ffc3901de09a9424. [Reporting paper]() Recorded evaluation configuration: {"Setup":"Embedding adaptation","Backbone":"ResNet"}. This record does not assert independent reproduction. ### ProtoNet Accuracy: 0.8053. Result ID: 698e12b0ffc3901de09a9422. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"Instance embedding","Backbone":"ResNet"}. This record does not assert independent reproduction. ### CTM Accuracy: 0.8051. Result ID: 698e12b0ffc3901de09a941e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet"}. This record does not assert independent reproduction. ### SimpleShot Accuracy: 0.8002. Result ID: 698e12b0ffc3901de09a9420. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet"}. This record does not assert independent reproduction. ### MetaOptNet Accuracy: 0.7863. Result ID: 698e12b0ffc3901de09a941d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet"}. This record does not assert independent reproduction. ### TADAM Accuracy: 0.767. Result ID: 698e12b0ffc3901de09a941c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet"}. This record does not assert independent reproduction. ### PFA Accuracy: 0.7374. Result ID: 698e12b0ffc3901de09a941b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet"}. This record does not assert independent reproduction. ### sparse-ReLU-MAML Accuracy: 0.7301. Result ID: 698e591cffc3901de09cd523. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-12","Number of seeds":"3"}. This record does not assert independent reproduction. ### FEAT Accuracy: 0.7161. Result ID: 698e12b0ffc3901de09a9429. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Setup":"Embedding adaptation","Backbone":"ConvNet"}. This record does not assert independent reproduction. ### ProtoNet Accuracy: 0.7133. Result ID: 698e12b0ffc3901de09a9421. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"Instance embedding","Backbone":"ConvNet"}. This record does not assert independent reproduction. ### DEEPSETS Accuracy: 0.7096. Result ID: 698e12b0ffc3901de09a9425. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"Embedding adaptation","Backbone":"ConvNet"}. This record does not assert independent reproduction. ### MetaOptNet Accuracy: 0.7088. Result ID: 698e591cffc3901de09cd51e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-12","Number of seeds":"3","Regularization":"None"}. This record does not assert independent reproduction. ### GCN Accuracy: 0.7059. Result ID: 698e12b0ffc3901de09a9427. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Setup":"Embedding adaptation","Backbone":"ConvNet"}. This record does not assert independent reproduction. ### BOIL Accuracy: 0.705. Result ID: 698e591cffc3901de09cd521. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-12","Number of seeds":"3"}. This record does not assert independent reproduction. ### ANIL Accuracy: 0.7003. Result ID: 698e591cffc3901de09cd520. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-12","Number of seeds":"3"}. This record does not assert independent reproduction. ### sparse-MAML Accuracy: 0.7002. Result ID: 698e591cffc3901de09cd522. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-12","Number of seeds":"3"}. This record does not assert independent reproduction. ### MAML Accuracy: 0.6936. Result ID: 698e591cffc3901de09cd51f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-12","Number of seeds":"3"}. This record does not assert independent reproduction. ### BILSTM Accuracy: 0.6915. Result ID: 698e12b0ffc3901de09a9423. [Reporting paper]() Recorded evaluation configuration: {"Setup":"Embedding adaptation","Backbone":"ConvNet"}. This record does not assert independent reproduction. ### ProtoNet Accuracy: 0.682. Result ID: 698e12b0ffc3901de09a9418. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ConvNet"}. This record does not assert independent reproduction. ### PFA Accuracy: 0.6787. Result ID: 698e12b0ffc3901de09a941a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ConvNet"}. This record does not assert independent reproduction. ### RelationNet Accuracy: 0.6707. Result ID: 698e12b0ffc3901de09a9419. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ConvNet"}. This record does not assert independent reproduction. ### SimpleShot Accuracy: 0.6692. Result ID: 698e12b0ffc3901de09a941f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ConvNet"}. This record does not assert independent reproduction. ### MAML Accuracy: 0.6311. Result ID: 698e12b0ffc3901de09a9417. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ConvNet"}. This record does not assert independent reproduction. ### MatchNet Accuracy: 0.5109. Result ID: 698e12b0ffc3901de09a9416. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ConvNet"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.