… in the training tasks, it is difficult to learn a good metric space. To reach the full potential
of metric based few-shot learning, we propose a large margin principle for learning a more …

… margin principle to improve the generalization ability of metric-based meta-learning
approaches for few-shot learning … Thus, the generator will add larger margin for relatively similar …

… margin loss to metric learning based few-shot learning methods. The negative margin loss
… As we expect, applying larger margin to softmax loss can achieve better accuracy on base …

Few-shot learning learns to classify unseen data with few training samples in hand and has
attracted increasing attentions recently. In this paper, we propose a novel Temperature …

… Few-shot Learning Existing few-shot learning methods can be broadly categorized as either…
reconstructed with the base classes and large margin would improve the diversity of novel …

… few-shot learning problem (CD-FSL), especially when huge … that few-shot methods still
need to fine-tune when a huge … -tuning method for few-shot models which generates pseudo …

… In this paper, we study the cause of such dilemma for the few-shot class-incremental learning
… This is because the few-shot training data could not provide sufficient information for novel-…

… We implement and compare several of the aforementioned loss functions for large margin
few-shot learning, including the normalized triplet loss, the normalized contrastive loss [7, 19], …

… significant. With both the new pFSL setting and novel IbM2 method, this paper shows that
practical few-shot learning … with the best C by a significant margin in all cases. Specifically, the …

… labeled instances for training. In this paper, we consider few-shot learning is of great practical
… improve a modern framework of metric learning for few-shot RC. Specifically, we adopt the …