Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition
2021 IEEE/CVF International Conference on Computer Vision (ICCV)(2021)
摘要
Many state-of-the-art few-shot learners focus on developing effective training procedures for feature representations, before using simple (e.g., nearest centroid) classifiers. We take an approach that is agnostic to the features used, and focus exclusively on meta-learning the final classifier layer. Specifically, we introduce MetaQDA, a Bayesian meta-learning generalisation of the classic quadra...
更多查看译文
关键词
Training,Representation learning,Measurement,Computer vision,Uncertainty,Memory management,Feature extraction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络