SSL-ProtoNet: Self-supervised Learning Prototypical Networks for few-shot learning

Jit Yan Lim, Kian-Ming Lim, Chin-Poo Lee, Yong Xuan Tan

Abstract: Highlights•A metric-based few-shot approach that leverages self-supervised learning.•A noisy transformation is proposed optimize the learned representation.•Self-supervised learning is proposed to enhance sample discrimination.•A self-supervised loss signal to preserve the representation diversity.•Knowledge in the model is further self-distilled for better performance.