“…Few-Shot Fine-Grained Learning (FSFGL). Recent FSL works [1,23,25,37,63,65,68] can be roughly categorized into three types: 1) Optimization-based methods [11,38] that focus on learning good initialization parameters in order to quickly adapt the few-shot model to novel classes; 2) Metric-based methods [35,41,43,48] that aim to design a distance metric, so that the few-shot model can learn the semantic relation between different input images; 3) Data augmentation-based methods [6,14,26,36,54,70] that produce new samples to enlarge the training set for model training. Recently, inspired by the rapid development of meta-learning, researchers [9, 12, 19, 27-29, 46, 50, 57, 58, 71] start to explore the generalization ability of FSL model on novel fine-grained subclasses where only a few training examples are given.…”