Fei-Fei, Li, Fergus, Robert, and Perona, Pietro. One-shot learning of object categories. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 28(4):594611, 2006.
The key insight is that, rather than learning from scratch, one can take advantage of knowledge coming from previously learned categories, no matter how different these categories might be.
实验
Bayesian implementation
101diverse object categories
Prototypical Networks
Snell, Jake et al. “Prototypical Networks for Few-shot Learning.” Neural Information Processing Systems (2017).
方法
创新点
适用领域&数据集
利弊
Matching Networks
Vinyals, Oriol et al. “Matching Networks for One Shot Learning.” Neural Information Processing Systems (2016).
Relation Network
Sung, Flood et al. “Learning to Compare: Relation Network for Few-Shot Learning.” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2017): 1199-1208.
Optimization as a Model for Few-Shot Learning
Ravi, Sachin and H. Larochelle. “Optimization as a Model for Few-Shot Learning.” International Conference on Learning Representations (2016).
TADAM: Task dependent adaptive metric for improved few-shot learning
Oreshkin, Boris N. et al. “TADAM: Task dependent adaptive metric for improved few-shot learning.” Neural Information Processing Systems (2018).