人だってモノを見るときに色んな角度から見たりクルクル回したりするのだから、学習用CNNの一層目に入力画像を振ったり回転させたりする手が生えてても別にいいのではと思ってる。
-
-
Replying to @ultraistter
@ultraistter Ever tried implementing some form of localized visual attention in your convnets?1 reply 0 retweets 0 likes -
Replying to @ultraistter
@ultraistter Visual attention being a way to *learn* optimal data augmentation schemes. Instead of using a bunch of random transforms.1 reply 0 retweets 2 likes
@ultraistter Humans get many "versions" of an input when looking at something, but these versions aren't random. Eye saccades are guided.
11:52 PM - 3 Feb 2015
0 replies
0 retweets
1 like
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.