Memory-Augmented Relation Network for Few-Shot Learning
MM '20: The 28th ACM International Conference on Multimedia Seattle WA USA October, 2020, pp. 1236-1244, 2020.
Metric-based few-shot learning methods concentrate on learning transferable feature embedding which generalizes well from seen categories to unseen categories under limited supervision. However, most of the methods treat each individual instance separately without considering its relationships with the others in the working context. We in...More
PPT (Upload PPT)