Harmonic mean: 73.07
Papers with Code · CC BY-SA 4.0
Meta-Learning
Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.
<span style="color:grey; opacity: 0.6">( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )</span>
논문
Meta-train success rate: 25%Meta-test success rate: 36%
Meta-train success rate: 74.9Meta-test success rate (zero-shot): 18.5
Acc: 93.5(0.5)
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: 73.42
Meta-test success rate: 5.4%
Average Success Rate: 26%
% Test Accuracy: 95.75
Accuracy: 77.9
Average Success Rate: 60.0%
Average Success Rate: 11%