FSPool: Learning set representations with featurewise sort pooling

Zhang, Yan, Hare, Jonathon and Prugel-Bennett, Adam (2019) FSPool: Learning set representations with featurewise sort pooling. Sets & Partitions: NeurIPS 2019 Workshop, Vancouver Convention Centre, West Level 2, #215-216, Vancouver, Canada. 14 Dec 2019.

Record type: Conference or Workshop Item (Paper)

Abstract

Traditional set prediction models can struggle with simple datasets due to an issue we call the responsibility problem. We introduce a pooling method for sets of feature vectors based on sorting features across elements of the set to learn better set representations. This can be used to construct a permutation-equivariant auto-encoder, which avoids the responsibility problem. 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.

Text

Paper - Version of Record

Available under License Creative Commons Attribution.

Download (435kB)

More information

Accepted/In Press date: 30 September 2019

Published date: 14 December 2019

Venue - Dates: Sets & Partitions: NeurIPS 2019 Workshop, Vancouver Convention Centre, West Level 2, #215-216, Vancouver, Canada, 2019-12-14 - 2019-12-14

Learn more about Vision, Learning and Control research Learn more about School of Electronics and Computer Science research