Harmonic mean: 73.07
Papers with Code · CC BY-SA 4.0
Few-Shot Learning
Few-Shot Learning is an example of meta-learning, where a learner is trained on several related tasks, during the meta-training phase, so that it can generalize well to unseen (but related) tasks with just few examples, during the meta-testing phase. An effective approach to the Few-Shot Learning problem is to learn a common representation for various tasks and train task specific classifiers on top of this representation.
<span class="description-source">Source: Penalty Method for Inversion-Free Deep Bilevel Optimization </span>
논문
Acc: 93.5(0.5)
Accuracy: 73.42
8-shot Accuracy: 82.64-shot Accuracy: 66.712-shot Accuracy: 88.816-shot Accuracy: 91.0
8-shot Accuracy: 71.84-shot Accuracy: 42.212-shot Accuracy: 82.916-shot Accuracy: 88.9
8-shot Accuracy: 73.14-shot Accuracy: 44.312-shot Accuracy: 83.916-shot Accuracy: 88.3
Accuracy: 65.7
5 way 1~2 shot: 74.74
Macro Precision: 0.9873Macro Recall: 0.9872Macro F1: 0.9872AUC-ROC: 0.9992
Accuracy: 82.75
Accuracy: 53.18
Accuracy: 77.9