# Cross-domain Few-shot Character Recognition on Omniglot to EMNIST (novel classes) Source: [Cross-domain Few-shot Character Recognition on Omniglot to EMNIST (novel classes)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:35.559Z Evaluation of cross-domain few-shot character recognition performance, transferring knowledge from Omniglot to novel classes in EMNIST. 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 | Cross-domain Few-shot Character Recognition | | Dataset (including any stated split) | Omniglot to EMNIST cross-domain (novel classes) | | 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 | | --- | --- | --- | --- | | RelationNet | 88.94 | Not recorded | 68fa66e41e209131cea12e8a | | MAML | 88.24 | Not recorded | 68fa66e41e209131cea12e8a | | MatchingNet | 87.6 | Not recorded | 68fa66e41e209131cea12e8a | | Baseline++ | 87.31 | Not recorded | 68fa66e41e209131cea12e8a | | ProtoNet | 87.04 | Not recorded | 68fa66e41e209131cea12e8a | | Baseline | 86 | Not recorded | 68fa66e41e209131cea12e8a | | RelationNet | 75.55 | Not recorded | 68fa66e41e209131cea12e8a | | MatchingNet | 72.71 | Not recorded | 68fa66e41e209131cea12e8a | | MAML | 72.04 | Not recorded | 68fa66e41e209131cea12e8a | | ProtoNet | 70.43 | Not recorded | 68fa66e41e209131cea12e8a | | Baseline++ | 64.74 | Not recorded | 68fa66e41e209131cea12e8a | | Baseline | 63.94 | Not recorded | 68fa66e41e209131cea12e8a | ### RelationNet Accuracy: 88.94. Result ID: 698d0e838b517eb4331eaa41. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"N-shot":"5-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way"}. This record does not assert independent reproduction. ### MAML Accuracy: 88.24. Result ID: 698d0e838b517eb4331eaa40. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N-shot":"5-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way"}. This record does not assert independent reproduction. ### MatchingNet Accuracy: 87.6. Result ID: 698d0e838b517eb4331eaa3e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"N-shot":"5-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way"}. This record does not assert independent reproduction. ### Baseline++ Accuracy: 87.31. Result ID: 698d0e838b517eb4331eaa3d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"N-shot":"5-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way","Training Epochs":5}. This record does not assert independent reproduction. ### ProtoNet Accuracy: 87.04. Result ID: 698d0e838b517eb4331eaa3f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N-shot":"5-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way"}. This record does not assert independent reproduction. ### Baseline Accuracy: 86. Result ID: 698d0e838b517eb4331eaa3c. [Reporting paper]() Recorded evaluation configuration: {"N-shot":"5-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way","Training Epochs":5}. This record does not assert independent reproduction. ### RelationNet Accuracy: 75.55. Result ID: 698d0e838b517eb4331eaa3b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"N-shot":"1-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way"}. This record does not assert independent reproduction. ### MatchingNet Accuracy: 72.71. Result ID: 698d0e838b517eb4331eaa38. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"N-shot":"1-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way"}. This record does not assert independent reproduction. ### MAML Accuracy: 72.04. Result ID: 698d0e838b517eb4331eaa3a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N-shot":"1-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way"}. This record does not assert independent reproduction. ### ProtoNet Accuracy: 70.43. Result ID: 698d0e838b517eb4331eaa39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N-shot":"1-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way"}. This record does not assert independent reproduction. ### Baseline++ Accuracy: 64.74. Result ID: 698d0e838b517eb4331eaa37. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"N-shot":"1-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way","Training Epochs":5}. This record does not assert independent reproduction. ### Baseline Accuracy: 63.94. Result ID: 698d0e838b517eb4331eaa36. [Reporting paper]() Recorded evaluation configuration: {"N-shot":"1-shot","Backbone":"Conv-4","Data Augmentation":"None","N-way":"5-way","Training Epochs":5}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.