Deep Set Prediction Networks
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.
Cite
Text
Zhang et al. "Deep Set Prediction Networks." Neural Information Processing Systems, 2019.Markdown
[Zhang et al. "Deep Set Prediction Networks." Neural Information Processing Systems, 2019.](https://mlanthology.org/neurips/2019/zhang2019neurips-deep/)BibTeX
@inproceedings{zhang2019neurips-deep,
title = {{Deep Set Prediction Networks}},
author = {Zhang, Yan and Hare, Jonathon and Prugel-Bennett, Adam},
booktitle = {Neural Information Processing Systems},
year = {2019},
pages = {3212-3222},
url = {https://mlanthology.org/neurips/2019/zhang2019neurips-deep/}
}