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.
Yan Zhang (University of Southampton)
Samsung @ Mila is hiring research scientists in an academic-style lab :)
Jonathon Hare (University of Southampton)
Adam Prugel-Bennett (firstname.lastname@example.org)
More from the Same Authors
2020 Poster: Linear Disentangled Representations and Unsupervised Action Estimation »
Matthew Painter · Adam Prugel-Bennett · Jonathon Hare