Prototype Rectification for Few-Shot Learning

2019/11/25 by Jinlu Liu, Liu, Jinlu, Liang Song +3 · 8 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning and ELM #Multimodal Machine Learning Applications #cs.CV

paper · pdf · doi:10.48550/arxiv.1911.10713

ECCV 2020 Oral

openalex publication_date 2019/11/25 · arxiv created 2020/07/13 · arxiv updated 2020/07/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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).

Citations

• ImageNet Large Scale Visual Recognition Challenge
• ImageNet classification with deep convolutional neural networks
• Prototypical Networks for Few-shot Learning
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Few-Shot Learning with Graph Neural Networks
• On First-Order Meta-Learning Algorithms
• Meta-learning with differentiable closed-form solvers
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• Infinite Mixture Prototypes for Few-Shot Learning
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network
• Language-Aware Information Maximization for Transductive Few-Shot CLIP
• Reliable Few-shot Learning under Dual Noises
• Performance Analysis of Few-Shot Learning Approaches for Bangla Handwritten Character and Digit Recognition
• Prototype Embedding Optimization for Human-Object Interaction Detection in Livestreaming
• ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations
• Sill-Net: Feature Augmentation with Separated Illumination Representation

Related

• Prototype Completion for Few-Shot Learning
• Shot in the Dark: Few-Shot Learning with No Base-Class Labels
• Learning Class-level Prototypes for Few-shot Learning
• A Closer Look at Prototype Classifier for Few-shot Image Classification
• Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis