Poster
Deep Set Prediction Networks
Yan Zhang · Jonathon Hare · Adam Prugel-Bennett
East Exhibition Hall B + C #54
Keywords: [ Algorithms -> Structured Prediction; Deep Learning -> Deep Autoencoders; Deep Learning ] [ Supervised Deep Networks ] [ Deep Learning ] [ Predictive Models ]
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.
Live content is unavailable. Log in and register to view live content