NeurIPS 2019poster139 citations
Deep Set Prediction Networks
Yan Zhang, Jonathon Hare, Adam Prugel-Bennett
Abstract
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.
BibTeX
@inproceedings{NEURIPS2019_6e79ed05,
author = {Zhang, Yan and Hare, Jonathon and Prugel-Bennett, Adam},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Deep Set Prediction Networks},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/6e79ed05baec2754e25b4eac73a332d2-Paper.pdf},
volume = {32},
year = {2019}
}