paper-with-me

홈 › Papers

Robust Collaborative Learning with Noisy Labels

2020-12-26 · Mengying Sun, Jing Xing, Bin Chen, Jiayu Zhou

Learning with curriculum has shown great effectiveness in tasks where the data contains noisy (corrupted) labels, since the curriculum can be used to re-weight or filter out noisy samples via proper design. However, obtaining curriculum from a learner itself without additional supervision or feedback deteriorates the effectiveness due to sample selection bias. Therefore, methods that involve two or more networks have been recently proposed to mitigate such bias. Nevertheless, these studies utilize the collaboration between networks in a way that either emphasizes the disagreement or focuses on the agreement while ignores the other. In this paper, we study the underlying mechanism of how disagreement and agreement between networks can help reduce the noise in gradients and develop a novel framework called Robust Collaborative Learning (RCL) that leverages both disagreement and agreement among networks. We demonstrate the effectiveness of RCL on both synthetic benchmark image data and real-world large-scale bioinformatics data.

📄 PDF Abstract BibTeX arXiv:2012.13670

Code (0)

등록된 구현이 없습니다.

Tasks

Learning with noisy labelsSelection bias

Similar Papers 제목 키워드 기반

Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLM-Powered Assistance

2025-04-03 · Bo Yuan, Yulin Chen, Yin Zhang, Wei Jiang

Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solutions identify noisy labels and adopt ac…

Active LearningDenoising

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

A Consensual Collaborative Learning Method for Remote Sensing Image Classification Under Noisy Multi-Labels

2021-05-12 · Ahmet Kerem Aksoy, Mahdyar Ravanbakhsh, Tristan Kreuziger, Begum Demir

Collecting a large number of reliable training images annotated by multiple land-cover class labels in the framework of multi-label classification is time-consuming and costly in remote sensing (RS). To address this prob…

image-classificationImage ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION+2

Collaborative Label Correction via Entropy Thresholding

2021-03-31 · Hao Wu, Jiangchao Yao, Jiajie Wang, Yinru Chen 외

Deep neural networks (DNNs) have the capacity to fit extremely noisy labels nonetheless they tend to learn data with clean labels first and then memorize those with noisy labels. We examine this behavior in light of the …

Learning to Complement with Multiple Humans

2023-11-22 · Zheng Zhang, Cuong Nguyen, Kevin Wells, Thanh-Toan Do 외

Real-world image classification tasks tend to be complex, where expert labellers are sometimes unsure about the classes present in the images, leading to the issue of learning with noisy labels (LNL). The ill-posedness o…

image-classificationImage ClassificationLearning with noisy labels