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...
Main Authors: | Owens, Andrew Hale, Wu, Jiajun, McDermott, Joshua H., Freeman, William T., Torralba, Antonio |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences |
Format: | Article |
Language: | en_US |
Published: |
Springer-Verlag
2017
|
Online Access: | http://hdl.handle.net/1721.1/111172 https://orcid.org/0000-0001-9020-9593 https://orcid.org/0000-0002-4176-343X https://orcid.org/0000-0002-3965-2503 https://orcid.org/0000-0002-2231-7995 https://orcid.org/0000-0003-4915-0256 |
Similar Items
-
Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning
by: Owens, Andrew, et al.
Published: (2021) -
Visually Indicated Sounds
by: Isola, Phillip, et al.
Published: (2017) -
Self-Supervised Audio-Visual Co-Segmentation
by: Rouditchenko, Andrew, et al.
Published: (2022) -
Self-Supervised Audio-Visual Co-Segmentation
by: Rouditchenko, Andrew, et al.
Published: (2021) -
The Sound of Pixels
by: Zhao, Hang, et al.
Published: (2020)