Deep set prediction networks
Deep set prediction networks
We study the problem of predicting a set from a feature vector with a deep neural network. Existing approaches ignore the set structure of the problem 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 bounding boxes of the set of objects in an image, and predict the attributes of these objects in an image.
Zhang, Yan
0edf84ab-1e32-4239-bef6-7fe80d6bc7a7
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
14 December 2019
Zhang, Yan
0edf84ab-1e32-4239-bef6-7fe80d6bc7a7
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
Zhang, Yan, Hare, Jonathon and Prugel-Bennett, Adam
(2019)
Deep set prediction networks.
Sets & Partitions: NeurIPS 2019 Workshop, Vancouver Convention Centre, West Level 2, #215-216, Vancouver, Canada.
14 Dec 2019.
Record type:
Conference or Workshop Item
(Paper)
Abstract
We study the problem of predicting a set from a feature vector with a deep neural network. Existing approaches ignore the set structure of the problem 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 bounding boxes of the set of objects in an image, and predict the attributes of these objects in an image.
Text
Paper
- Version of Record
More information
Accepted/In Press date: 30 September 2019
Published date: 14 December 2019
Venue - Dates:
Sets & Partitions: NeurIPS 2019 Workshop, Vancouver Convention Centre, West Level 2, #215-216, Vancouver, Canada, 2019-12-14 - 2019-12-14
Identifiers
Local EPrints ID: 434823
URI: http://eprints.soton.ac.uk/id/eprint/434823
PURE UUID: b6776acc-fdfd-4754-a8c6-fcc6a377e14a
Catalogue record
Date deposited: 11 Oct 2019 16:30
Last modified: 17 Mar 2024 03:05
Export record
Contributors
Author:
Yan Zhang
Author:
Jonathon Hare
Author:
Adam Prugel-Bennett
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics