Computer vision has made impressive gains through the use of deep learning models trained with large-scale labeled data. However, labels require expertise and curation and are expensive to collect. Can one discover useful visual representations without the use of explicitly curated labels?
Alyosha Efros shares several case studies exploring the paradigm of self-supervised learning (using raw data as its own supervision) and discusses several ways of defining objective functions in high-dimensional spaces, including the use of general adversarial networks (GANs) to learn the objective function directly from the data. Alyosha also covers the applications of this technology for image synthesis, including automatic colorization, image-to-image translation, curiosity-based exploration, and, terrifyingly, #edges2cats.
Alexei (Alyosha) Efros is an associate professor of electrical engineering and computer science at UC Berkeley. Previously, Alyosha spent nine years on the faculty of Carnegie Mellon University and has also been affiliated with École Normale Supérieure/Inria and the University of Oxford. Alyosha’s research is in the areas of computer vision and computer graphics, especially at their intersection. He is particularly interested in using data-driven techniques to tackle problems that are very hard to model parametrically but where large quantities of data are readily available. His awards include a CVPR Best Paper Award (2006), a NSF CAREER award (2006), a Sloan fellowship (2008), a Guggenheim fellowship (2008), an Okawa grant (2008), the Finmeccanica Career Development Chair (2010), the SIGGRAPH Significant New Researcher Award (2010), an ECCV Best Paper honorable mention (2010), and the Helmholtz Test-of-Time Prize (2013). Alyosha holds a PhD from UC Berkeley.
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com