Prototype Rectification for Few-Shot Learning
It addresses prototype bias in few-shot learning for AI systems, offering incremental improvements over existing methods.
The paper tackles the problem of biased prototypes in few-shot learning by identifying intra-class and cross-class biases and proposing a rectification method using label propagation and feature shifting. It achieves state-of-the-art performance on benchmarks, such as 70.31% on 1-shot and 81.89% on 5-shot for miniImageNet.
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).