Papers with Code · CC BY-SA 4.0

Few-Shot Learning

Meta-Learning › Few-Shot Learning 681 평가 기록 69 datasets

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>

하위 태스크

FS Few-Shot Semantic Segmentation 17 데이터셋 · 480 rows CF Cross-Domain Few-Shot 10 데이터셋 · 77 rows FA Few-Shot Audio Classification 10 데이터셋 · 67 rows FR Few-Shot Relation Classification 4 데이터셋 · 4 rows OL One-Shot Learning 1 데이터셋 · 1 rows FC Few-Shot Camera-Adaptive Color Constancy 0 데이터셋 · 0 rows FI Few-Shot Imitation Learning 0 데이터셋 · 0 rows FV Few-Shot Video Object Detection 0 데이터셋 · 0 rows FH Few-shot HTC 0 데이터셋 · 0 rows UF Unsupervised Few-Shot Audio Classification 0 데이터셋 · 0 rows UF Unsupervised Few-Shot Learning 0 데이터셋 · 0 rows F few-shot-htc 0 데이터셋 · 0 rows