Deep set prediction networks
Deep set prediction networks
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.
set prediction, deep learning
1-11
Zhang, Yan
0edf84ab-1e32-4239-bef6-7fe80d6bc7a7
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
8 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.
2019 Conference on Neural Information Processing Systems, Vancouver Convention Center, Vancouver, Canada.
08 - 14 May 2019.
.
Record type:
Conference or Workshop Item
(Paper)
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.
Text
Paper
- Accepted Manuscript
Text
8584-deep-set-prediction-networks
- Version of Record
Restricted to Repository staff only
Request a copy
More information
Accepted/In Press date: 4 September 2019
Published date: 8 December 2019
Venue - Dates:
2019 Conference on Neural Information Processing Systems, Vancouver Convention Center, Vancouver, Canada, 2019-05-08 - 2019-05-14
Keywords:
set prediction, deep learning
Identifiers
Local EPrints ID: 434826
URI: http://eprints.soton.ac.uk/id/eprint/434826
PURE UUID: 9daf45d4-018c-4fad-af98-0f70b40204b4
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