Mean IoU: 90.8FB-IoU: 94.4
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
Mean IoU: 91.7
Accuracy: 25.262
Accuracy: 73.2
8-shot Accuracy: 54.84-shot Accuracy: 48.312-shot Accuracy: 58.116-shot Accuracy: 60.2
Acc: 74.74
Harmonic mean: 67.27
Accuracy: 25.458
Accuracy: 24.924
Accuracy: 25.058
Accuracy: 25.547
Mean IoU: 90.6
8-shot Accuracy: 50.44-shot Accuracy: 40.912-shot Accuracy: 54.616-shot Accuracy: 57.4
Mean IoU: 90.4FB-IoU: 94.1
Acc: 67.6
Accuracy: 61.911
Mean IoU: 90.5
8-shot Accuracy: 50.64-shot Accuracy: 41.512-shot Accuracy: 54.516-shot Accuracy: 57.4
Accuracy: 41.476
Accuracy: 25.653
Accuracy: 25.627
Accuracy: 97.5
Accuracy: 24.942
Accuracy: 87.4%
Accuracy: 25.058