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。
@ultraistter Ever tried implementing some form of localized visual attention in your convnets?
-
-
@fchollet no. I was referring to data augmentation. -
@ultraistter Visual attention being a way to *learn* optimal data augmentation schemes. Instead of using a bunch of random transforms. - Show replies
New conversation -
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.