Detecting symmetry in small images with RNN



My network works on 32x32 normalized (translationally) but noisy images. Its task it to determine whether image has simple symmetry (horizontal/vertical). It needs to be reasonably robust to rotation (up to 20 degrees).

I approached this task with a simple perceptron-like net with 2 hidden layers. It performs reasonably well (on limited amount of data that I have) but I can't shake off the feeling that this design is absolutely the worst for what i need.

  1. It is hard to judge generalization capacity of the net (overfits really easily)
  2. It performs alot worse than a simple deterministic program that i wrote for the same task

Symmetry is such a simple concept but my neural network (being feed forward type) can't represent it efficiently. What I have in mind is a kind of RNN that decides what axis to fold the image along and then judging on how well folded parts of image match. Are there papers on something like that?

Andrew Butenko

Posted 2017-10-05T05:42:13.597

Reputation: 221

No answers