Deep Set Prediction Networks

TL;DR

This paper introduces a novel deep learning model for set prediction that inherently respects the unordered nature of sets, effectively handling tasks like auto-encoding point sets and object attribute prediction.

Contribution

The proposed model addresses the limitations of previous methods by properly modeling set structures and avoiding discontinuity issues, enabling accurate set predictions from a single feature vector.

Findings

Successfully auto-encodes point sets

Predicts object bounding boxes in images

Predicts object attributes accurately

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.