FSPool: Learning Set Representations with Featurewise Sort Pooling

06/06/2019
by   Yan Zhang, et al.
0

We introduce a pooling method for sets of feature vectors based on sorting features across elements of the set. This allows a deep neural network for sets to learn more flexible representations. We also demonstrate how FSPool can be used to construct a permutation-equivariant auto-encoder. On a toy dataset of polygons and a set version of MNIST, we show that such an auto-encoder produces considerably better reconstructions. Used in set classification, FSPool significantly improves accuracy and convergence speed on the set versions of MNIST and CLEVR.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset