Skip to yearly menu bar Skip to main content


Poster

Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks

Arash Vahdat

Pacific Ballroom #132

Keywords: [ Semi-Supervised Learning ] [ Deep Learning ]


Abstract:

Collecting large training datasets, annotated with high-quality labels, is costly and time-consuming. This paper proposes a novel framework for training deep convolutional neural networks from noisy labeled datasets that can be obtained cheaply. The problem is formulated using an undirected graphical model that represents the relationship between noisy and clean labels, trained in a semi-supervised setting. In our formulation, the inference over latent clean labels is tractable and is regularized during training using auxiliary sources of information. The proposed model is applied to the image labeling problem and is shown to be effective in labeling unseen images as well as reducing label noise in training on CIFAR-10 and MS COCO datasets.

Live content is unavailable. Log in and register to view live content