PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 31, 2017119 citationsOpen Access

Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks

AVArash Vahdat

Key Points

Key points are not available for this paper at this time.

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.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Arash Vahdat (2017) studied this question.

synapsesocial.com/papers/6a16144728acfec847bf8d8dhttps://doi.org/10.48550/arxiv.1706.00038
Ask AI
Helpful
Bookmark
Share
View Full Paper