Poster
Deep Set Prediction Networks
Yan Zhang · Jonathon Hare · Adam Prugel-Bennett
Keywords: [ Predictive Models ] [ Deep Learning ] [ Supervised Deep Networks ] [ Algorithms -> Structured Prediction; Deep Learning -> Deep Autoencoders; Deep Learning ]
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.