Joint Optimization Framework for Learning with Noisy Labels
Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy labels. Training on such noisy labeled datasets causes performance degradation because DNNs easily overfit to noisy labels. To overcome this problem, we propose a joint optimization framework of learning DNN parameters and estimating true labels. Our framework can correct labels during training by alternating update of network parameters and labels. We conduct experiments on the noisy CIFAR-10 datasets and the Clothing1M dataset. The results indicate that our approach significantly outperforms other state-of-the-art methods.
Code (1)
Tasks
General Classificationimage-classificationImage ClassificationLearning with noisy labelsSimilar Papers 제목 키워드 기반
Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels
Severity level estimation is a crucial task in medical image diagnosis. However, accurately assigning severity class labels to individual images is very costly and challenging. Consequently, the attached labels tend to b…
Meta Label Correction for Noisy Label Learning
Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. Its importance has further increased recently due to the growing need for large-scale datas…
Image ClassificationLearning with noisy labelsMeta-Learningtext-classification+1Improved Mix-up with KL-Entropy for Learning From Noisy Labels
Despite the deep neural networks (DNN) has achieved excellent performance in image classification researches, the training of DNNs needs a large of clean data with accurate annotations. The collect of a dataset is easy, …
image-classificationImage ClassificationA Novel Perspective for Positive-Unlabeled Learning via Noisy Labels
Positive-unlabeled learning refers to the process of training a binary classifier using only positive and unlabeled data. Although unlabeled data can contain positive data, all unlabeled data are regarded as negative dat…
Learning from Noisy Labels for Entity-Centric Information Extraction
Recent information extraction approaches have relied on training deep neural models. However, such models can easily overfit noisy labels and suffer from performance degradation. While it is very costly to filter noisy l…
Named Entity Recognition (NER)Relation Extraction