Robust Collaborative Learning with Noisy Labels
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Learning with noisy labelsSelection biasSimilar Papers 제목 키워드 기반
Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLM-Powered Assistance
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 LearningDenoisingImbalanced Medical Image Segmentation with Pixel-dependent Noisy Labels
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 SegmentationA Consensual Collaborative Learning Method for Remote Sensing Image Classification Under Noisy Multi-Labels
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+2Collaborative Label Correction via Entropy Thresholding
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
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