Large Margin Few-Shot Learning
The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework to learn a more discriminative metric space by augmenting the classification loss function with a large margin distance loss function for training. Extensive experiments on two state-of-the-art few-shot learning methods, graph neural networks and prototypical networks, show that our method can improve the performance of existing models substantially with very little computational overhead, demonstrating the effectiveness of the large margin principle and the potential of our method.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot LearningGeneral ClassificationSimilar Papers 제목 키워드 기반
Boosting Transductive Few-Shot Fine-Tuning With Margin-Based Uncertainty Weighting and Probability Regularization
Few-Shot Learning (FSL) has been rapidly developed in recent years, potentially eliminating the requirement for significant data acquisition. Few-shot fine-tuning has been demonstrated to be practically efficient and…
Few-Shot LearningLarge Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learning
In recent years, few-shot learning problems have received a lot of attention. While methods in most previous works were trained and tested on datasets in one single domain, cross-domain few-shot learning is a brand-new b…
Cross-Domain Few-Shotcross-domain few-shot learningFace RecognitionFew-Shot LearningA Transductive Maximum Margin Classifier for Few-Shot Learning
Few-shot learning aims to train a classifier that can generalize well when just a small number of labeled examples per class are given. We introduce a transductive maximum margin classifier for few-shot learning (FS-TMMC…
Few-Shot LearningNegative Margin Matters: Understanding Margin in Few-shot Classification
This paper introduces a negative margin loss to metric learning based few-shot learning methods. The negative margin loss significantly outperforms regular softmax loss, and achieves state-of-the-art accuracy on three st…
ClassificationFew-Shot Image ClassificationFew-Shot LearningGeneral Classification+1Large Margin Prototypical Network for Few-shot Relation Classification with Fine-grained Features
Relation classification (RC) plays a pivotal role in both natural language understanding and knowledge graph completion. It is generally formulated as a task to recognize the relationship between two entities of interest…
Feature EngineeringFew-Shot LearningFew-Shot Relation ClassificationKnowledge Graph Completion+5