Training Convolutional Networks with Noisy Labels

• DOI: 10.48550/arxiv.1406.2080
• Publication Date: 2014-01-01
• Authors: Sainbayar Sukhbaatar; Joan Bruna; Manohar Paluri; Lubomir Bourdev; Rob Fergus
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; 0202 electrical engineering, electronic engineering, information engineering; Computer Science - Neural and Evolutionary Computing; 02 engineering and technology; Neural and Evolutionary Computing (cs.NE); Machine Learning (cs.LG)

The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results. However, in many settings manual annotation the data is impractical; instead our noisy labels, i.e. there some freely available label for each image which may or not be accurate. In this paper, we explore performance discriminatively-trained Convnets when trained on such data. We introduce an extra noise layer into network adapts outputs match distribution. parameters can estimated as part training process and involve simple modifications current infrastructures deep networks. demonstrate approaches several datasets, including scale experiments ImageNet classification benchmark.