A simple scheme to amplify inter-class discrepancy for improving few-shot fine-grained image classification

Xiaoxu Li, Zijie Guo, Rui Zhu, Zhanyu Ma, Jun Guo, Jing-Hao Xue

Abstract: Highlights•We propose AFRN, a simple scheme to amplify inter-class discrepancy.•We relax the inter-class score in TDM to mitigate the negative impact of overfitting.•We incorporate the guidance of the centre loss to FRN to enhance the discriminative power of learnt features.•The experimental results demonstrate that our scheme is simple yet effective to improve the few-shot classification performance.