paper-with-me

홈 › Papers

Few-shot Learning with Noisy Labels

2022-04-12 · CVPR 2022 1 · Kevin J Liang, Samrudhdhi B. Rangrej, Vladan Petrovic, Tal Hassner

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.

📄 PDF Abstract BibTeX arXiv:2204.05494

Code (1)

facebookresearch/noisy_few_shot 공식 구현 pytorch

Tasks

Few-Shot LearningLearning with noisy labels

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

CRoF: CLIP-based Robust Few-shot Learning on Noisy Labels

2024-12-17 · Shizhuo Deng, Bowen Han, Jiaqi Chen, Hao Wang 외

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 Learning

Graph convolutional networks for learning with few clean and many noisy labels

2019-10-01 · ECCV 2020 8 · Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum 외

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 Classification

Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement

2025-05-26 · Liqin Ye, Agam Shah, Chao Zhang, Sudheer Chava

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…

Benchmarking

Multi-label audio classification with a noisy zero-shot teacher

2024-07-20 · Sebastian Braun, Hannes Gamper

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 Augmentation

Transductive CLIP with Class-Conditional Contrastive Learning

2022-06-13 · Junchu Huang, WeiJie Chen, Shicai Yang, Di Xie 외

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