TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Image Classification	Clothing1M	Joint Opt.	Accuracy	72.23%	# 39

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/joint-optimization-framework-for-learning/image-classification-on-clothing1m)](https://paperswithcode.com/sota/image-classification-on-clothing1m?p=joint-optimization-framework-for-learning)`

Joint Optimization Framework for Learning with Noisy Labels

CVPR 2018 · 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.