Joint Optimization Framework for Learning with Noisy Labels

Autor:	Tanaka, Daiki, Ikami, Daiki, Yamasaki, Toshihiko, Aizawa, Kiyoharu
Rok vydání:	2018
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Statistics - Machine Learning
Zdroj:	CVPR 2018, pp.5552--5550
Druh dokumentu:	Working Paper
Popis:	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. Comment: To appear at CVPR 2018 (poster), including supplementary material
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1803.11364 Zobrazit plný text záznamu View this record from Arxiv