Still vastly underused in image to image to this day and I don't understand why: Unets and self-attention. I keep seeing papers come out that have obvious problems that could be solved using these two simple things!
-
Care to elaborate?
1/ Sure. A basic problem I keep seeing with image to image papers is that there's a lack of long range consistency in objects. That's what attention does for you. It's a very simple "add in" to your network, yet it does wonders.
-
-
I agree about self-attention, but UNets are underused, really?
-
I guess I'm hypersensitive to whenever I don't seen them being used...? Like I keep seeing colorization work that doesn't use them.
- 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.