Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Enhancing Deep Learning with Visual Interactions

Enhancing Deep Learning with Visual Interactions Deep learning has emerged as a powerful tool for feature-driven labeling of datasets. However, for it to be effective, it requires a large and finely labeled training dataset. Precisely labeling a large training dataset is expensive, time-consuming, and error prone. In this article, we present a visually driven deep-learning approach that starts with a coarsely labeled training dataset and iteratively refines the labeling through intuitive interactions that leverage the latent structures of the dataset. Our approach can be used to (a) alleviate the burden of intensive manual labeling that captures the fine nuances in a high-dimensional dataset by simple visual interactions, (b) replace a complicated (and therefore difficult to design) labeling algorithm by a simpler (but coarse) labeling algorithm supplemented by user interaction to refine the labeling, or (c) use low-dimensional features (such as the RGB colors) for coarse labeling and turn to higher-dimensional latent structures that are progressively revealed by deep learning, for fine labeling. We validate our approach through use cases on three high-dimensional datasets and a user study. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Interactive Intelligent Systems (TiiS) Association for Computing Machinery

Loading next page...
 
/lp/association-for-computing-machinery/enhancing-deep-learning-with-visual-interactions-OsEsfcAuaF
Publisher
Association for Computing Machinery
Copyright
Copyright © 2019 ACM
ISSN
2160-6455
eISSN
2160-6463
DOI
10.1145/3150977
Publisher site
See Article on Publisher Site

Abstract

Deep learning has emerged as a powerful tool for feature-driven labeling of datasets. However, for it to be effective, it requires a large and finely labeled training dataset. Precisely labeling a large training dataset is expensive, time-consuming, and error prone. In this article, we present a visually driven deep-learning approach that starts with a coarsely labeled training dataset and iteratively refines the labeling through intuitive interactions that leverage the latent structures of the dataset. Our approach can be used to (a) alleviate the burden of intensive manual labeling that captures the fine nuances in a high-dimensional dataset by simple visual interactions, (b) replace a complicated (and therefore difficult to design) labeling algorithm by a simpler (but coarse) labeling algorithm supplemented by user interaction to refine the labeling, or (c) use low-dimensional features (such as the RGB colors) for coarse labeling and turn to higher-dimensional latent structures that are progressively revealed by deep learning, for fine labeling. We validate our approach through use cases on three high-dimensional datasets and a user study.

Journal

ACM Transactions on Interactive Intelligent Systems (TiiS)Association for Computing Machinery

Published: Mar 1, 2019

Keywords: Deep learning

References