Poster
Deep Set Prediction Networks
Yan Zhang · Jonathon Hare · Adam Prugel-Bennett

Tue Dec 10th 05:30 -- 07:30 PM @ East Exhibition Hall B + C #54

Current approaches for predicting sets from feature vectors ignore the unordered nature of sets and suffer from discontinuity issues as a result. We propose a general model for predicting sets that properly respects the structure of sets and avoids this problem. With a single feature vector as input, we show that our model is able to auto-encode point sets, predict the set of bounding boxes of objects in an image, and predict the set of attributes of these objects.

Author Information

Yan Zhang (University of Southampton)
Jonathon Hare (University of Southampton)
Adam Prugel-Bennett (apb@ecs.soton.ac.uk)