paper-with-me

홈 › Papers

Joint Optimization Framework for Learning with Noisy Labels

2018-03-30 · CVPR 2018 6 · Daiki Tanaka, Daiki Ikami, Toshihiko Yamasaki, Kiyoharu Aizawa

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.

📄 PDF Abstract BibTeX arXiv:1803.11364

Code (1)

DaikiTanaka-UT/JointOptimization

Tasks

General Classificationimage-classificationImage ClassificationLearning with noisy labels

Similar Papers 제목 키워드 기반

Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels

2024-10-29 · Shumpei Takezaki, Kiyohito Tanaka, Seiichi Uchida

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

2019-11-10 · Guoqing Zheng, Ahmed Hassan Awadallah, Susan Dumais

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+1

Improved Mix-up with KL-Entropy for Learning From Noisy Labels

2019-08-15 · Qian Zhang, Feifei Lee, Ya-Gang Wang, Qiu Chen

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 Classification

A Novel Perspective for Positive-Unlabeled Learning via Noisy Labels

2021-03-08 · Daiki Tanaka, Daiki Ikami, Kiyoharu Aizawa

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

2021-04-17 · EMNLP 2021 11 · Wenxuan Zhou, Muhao Chen

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