Prototype Rectification for Few-Shot Learning
Preprint
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 two 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).Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Boosting Few-Shot Visual Learning With Self-Supervision2019
- Edge-Labeling Graph Neural Network for Few-Shot Learning2019
- Meta-Learning With Differentiable Convex Optimization2019
- Learning to Compare: Relation Network for Few-Shot Learning2018
- Few-Shot Image Recognition by Predicting Parameters from Activations2018
- Dynamic Few-Shot Visual Learning Without Forgetting2018
- Deep Domain Adaptation by Geodesic Distance Minimization2017
- Deep Residual Learning for Image Recognition2016
- Optimal Decisions from Probabilistic Models: The Intersection-over-Union Case2014
- Learning from one example through shared densities on transforms2002