UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

DiverseNet: When One Right Answer is not Enough

Firman, M; Campbell, NDF; Agapito, L; Brostow, GJ; (2018) DiverseNet: When One Right Answer is not Enough. In: Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. (pp. pp. 5598-5607). IEEE: Salt Late City, UT, USA. Green open access

[img]
Preview
Text
cvpr18_diversenet.pdf - Published version

Download (1MB) | Preview

Abstract

Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is subject to human labeling bias. Similarly, there are multiple possible pixel values that could plausibly complete occluded image regions. State-of-the art supervised learning methods are typically optimized to make a single test-time prediction for each query, failing to find other modes in the output space. Existing methods that allow for sampling often sacrifice speed or accuracy. We introduce a simple method for training a neural network, which enables diverse structured predictions to be made for each test-time query. For a single input, we learn to predict a range of possible answers. We compare favorably to methods that seek diversity through an ensemble of networks. Such stochastic multiple choice learning faces mode collapse, where one or more ensemble members fail to receive any training signal. Our best performing solution can be deployed for various tasks, and just involves small modifications to the existing single-mode architecture, loss function, and training regime. We demonstrate that our method results in quantitative improvements across three challenging tasks: 2D image completion, 3D volume estimation, and flow prediction.

Type: Proceedings paper
Title: DiverseNet: When One Right Answer is not Enough
Event: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Location: Salt Lake City, UT
Dates: 18 June 2018 - 23 June 2018
ISBN-13: 978-1-5386-6420-9
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/CVPR.2018.00587
Publisher version: https://doi.org/10.1109/CVPR.2018.00587
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Training, Task analysis, Aerospace electronics, Three-dimensional displays, Supervised learning, Two dimensional displays, Training data
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10074121
Downloads since deposit
48Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item