paper-with-me

Papers

Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning

2023-10-24 · Qing Miao, Xiaohe Wu, Chao Xu, Yanli Ji, WangMeng Zuo, Yiwen Guo, Zhaopeng Meng

Learning with noisy labels (LNL) has been extensively studied, with existing approaches typically following a framework that alternates between clean sample selection and semi-supervised learning (SSL). However, this approach has a limitation: the clean set selected by the Deep Neural Network (DNN) classifier, trained through self-training, inevitably contains noisy samples. This mixture of clean and noisy samples leads to misguidance in DNN training during SSL, resulting in impaired generalization performance due to confirmation bias caused by error accumulation in sample selection. To address this issue, we propose a method called Collaborative Sample Selection (CSS), which leverages the large-scale pre-trained model CLIP. CSS aims to remove the mixed noisy samples from the identified clean set. We achieve this by training a 2-Dimensional Gaussian Mixture Model (2D-GMM) that combines the probabilities from CLIP with the predictions from the DNN classifier. To further enhance the adaptation of CLIP to LNL, we introduce a co-training mechanism with a contrastive loss in semi-supervised learning. This allows us to jointly train the prompt of CLIP and the DNN classifier, resulting in improved feature representation, boosted classification performance of DNNs, and reciprocal benefits to our Collaborative Sample Selection. By incorporating auxiliary information from CLIP and utilizing prompt fine-tuning, we effectively eliminate noisy samples from the clean set and mitigate confirmation bias during training. Experimental results on multiple benchmark datasets demonstrate the effectiveness of our proposed method in comparison with the state-of-the-art approaches.

📄 PDF Abstract BibTeX arXiv:2310.15533

Code (0)

등록된 구현이 없습니다.

Tasks

Learning with noisy labels

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Imbalanced Medical Image Segmentation with Pixel-dependent Noisy Labels

2025-01-12 · Erjian Guo, Zicheng Wang, Zhen Zhao, Luping Zhou

Accurate medical image segmentation is often hindered by noisy labels in training data, due to the challenges of annotating medical images. Prior research works addressing noisy labels tend to make class-dependent assump…

Image SegmentationMedical Image SegmentationSemantic Segmentation

PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels

2024-12-18 · Pattern Recognition 2024 12 · Qian Zhang, Yi Zhu, Filipe R. Cordeiro, Qiu Chen

Large-scale image datasets frequently contain unavoidable noisy labels, resulting in overfitting in deep neural networks and declining performance. Most existing methods for learning from noisy labels operate as one-stag…

Image ClassificationLearning with noisy labels

A Framework using Contrastive Learning for Classification with Noisy Labels

2021-04-19 · Madalina Ciortan, Romain Dupuis, Thomas Peel

We propose a framework using contrastive learning as a pre-training task to perform image classification in the presence of noisy labels. Recent strategies such as pseudo-labeling, sample selection with Gaussian Mixture …

Contrastive LearningGeneral Classificationimage-classificationImage Classification

RankMatch: Fostering Confidence and Consistency in Learning with Noisy Labels

2023-01-01 · ICCV 2023 1 · Ziyi Zhang, Weikai Chen, Chaowei Fang, Zhen Li 외

Learning with noisy labels (LNL) is one of the most important and challenging problems in weakly-supervised learning. Recent advances adopt the sample selection strategy to mitigate the interference of noisy labels a…

Learning with noisy labelsRepresentation LearningWeakly-supervised Learning

Jo-SRC: A Contrastive Approach for Combating Noisy Labels

2021-03-24 · CVPR 2021 1 · Yazhou Yao, Zeren Sun, Chuanyi Zhang, Fumin Shen 외

Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels usually results in inferior model performance. Existing state-of-the-art methods primarily adopt a sample selection strategy, whic…

Contrastive LearningMemorization