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.
@article{arxiv.1906.06565,
title = {Deep Set Prediction Networks},
author = {Yan Zhang and Jonathon Hare and Adam Prügel-Bennett},
journal= {arXiv preprint arXiv:1906.06565},
year = {2020}
}