Supervision Beyond Manual Annotations for Learning Visual Representations
For both humans and machines, understanding the visual world requires relating new percepts with past experience. We argue that a good visual representation for an image should encode what makes it similar to other images, enabling the recall of associated experiences. Current machine implementation...
Main Author: | |
---|---|
Format: | Others |
Published: |
Research Showcase @ CMU
2016
|
Subjects: | |
Online Access: | http://repository.cmu.edu/dissertations/787 http://repository.cmu.edu/cgi/viewcontent.cgi?article=1826&context=dissertations |