Ambient Sound Provides Supervision for Visual Learning

The sound of crashing waves, the roar of fast-moving cars - sound conveys important information about the objects in our surroundings. In this work, we show that ambient sounds can be used as a supervisory signal for learning visual models. To demonstrate this, we train a convolutional neural networ...

Full description

Bibliographic Details
Main Authors: Owens, Andrew Hale (Contributor), Wu, Jiajun (Contributor), McDermott, Joshua H. (Contributor), Freeman, William T. (Contributor), Torralba, Antonio (Contributor)
Other Authors: Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
Format: Article
Language:English
Published: Springer-Verlag, 2017-09-12T13:32:52Z.
Subjects:
Online Access:Get fulltext