Using time as a supervision mechanism for self-supervised learning:https://arxiv.org/abs/1605.08104
-
-
Replying to @fchollet
Using spatial relationships: http://arxiv.org/abs/1603.09246
1 reply 3 retweets 17 likes -
Replying to @fchollet
It is likely that humans rely on both temporal continuity and spatial coherence to learn about visual features. So why not combine both?
4 replies 1 retweet 9 likes
This was a cool paper on the same theme too: https://arxiv.org/abs/1511.06811 "Learning visual groups from co-occurrences in space and time"
0 replies
11 retweets
22 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.