Few-shot Learning with Noisy Labels
Few-shot learning (FSL) methods typically assume clean support sets with accurately labeled samples when training on novel classes. This assumption can often be unrealistic: support sets, no matter how small, can still include mislabeled samples. Robustness to label noise is therefore essential for FSL methods to be practical, but this problem surprisingly remains largely unexplored. To address mislabeled samples in FSL settings, we make several technical contributions. (1) We offer simple, yet effective, feature aggregation methods, improving the prototypes used by ProtoNet, a popular FSL technique. (2) We describe a novel Transformer model for Noisy Few-Shot Learning (TraNFS). TraNFS leverages a transformer's attention mechanism to weigh mislabeled versus correct samples. (3) Finally, we extensively test these methods on noisy versions of MiniImageNet and TieredImageNet. Our results show that TraNFS is on-par with leading FSL methods on clean support sets, yet outperforms them, by far, in the presence of label noise.
Code (1)
Tasks
Few-Shot LearningLearning with noisy labelsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CRoF: CLIP-based Robust Few-shot Learning on Noisy Labels
Noisy labels threaten the robustness of few-shot learning (FSL) due to the inexact features in a new domain. CLIP, a large-scale vision-language model, performs well in FSL on image-text embedding similarities, but it is…
Domain GeneralizationFew-Shot Learningzero-shot-classificationZero-Shot LearningGraph convolutional networks for learning with few clean and many noisy labels
In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a graph per class and Graph Convolutional N…
Few-Shot LearningGeneral ClassificationCalibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement
The traditional process of creating labeled datasets is labor-intensive and expensive. Recent breakthroughs in open-source large language models (LLMs) have opened up a new avenue in generating labeled datasets automatic…
BenchmarkingMulti-label audio classification with a noisy zero-shot teacher
We propose a novel training scheme using self-label correction and data augmentation methods designed to deal with noisy labels and improve real-world accuracy on a polyphonic audio content detection task. The augmentati…
Audio ClassificationData AugmentationTransductive CLIP with Class-Conditional Contrastive Learning
Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervision i…
Contrastive LearningPseudo LabelZero-shot Generalization