Prototype Rectification for Few-Shot Learning

Abstract

Few-shot learning requires to recognize novel classes with scarce labeled data. Prototypical network is useful in existing researches, however, training on narrow-size distribution of scarce data usually tends to get biased prototypes. In this paper, we figure out two key influencing factors of the process: the intra-class bias and the cross-class bias. We then propose a simple yet effective approach for prototype rectification in transductive setting. The approach utilizes label propagation to diminish the intra-class bias and feature shifting to diminish the cross-class bias. We also conduct theoretical analysis to derive its rationality as well as the lower bound of the performance. Effectiveness is shown on three few-shot benchmarks. Notably, our approach achieves state-of-the-art performance on both miniImageNet (70.31% on 1-shot and 81.89% on 5-shot) and tieredImageNet (78.74% on 1-shot and 86.92% on 5-shot).

arXiv commentECCV 2020 Oral

References in corpus (10)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• A Simple Neural Attentive Meta-Learner
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• On First-Order Meta-Learning Algorithms
• Few-Shot Learning with Graph Neural Networks
• Learning to Self-Train for Semi-Supervised Few-Shot Classification
• Meta-learning with differentiable closed-form solvers
• Infinite Mixture Prototypes for Few-Shot Learning

Cited by in corpus (5)

• Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
• Sill-Net: Feature Augmentation with Separated Illumination Representation
• Dual-Awareness Attention for Few-Shot Object Detection
• MM-FSOD: Meta and metric integrated few-shot object detection
• Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification