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

UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory

Kokkinos, I; (2017) UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory. In: (Proceedings) 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). (pp. pp. 5454-5463). IEEE Green open access

[thumbnail of Kokkinos_Ubernet_Training_a_CVPR_2017_paper.pdf]
Preview
Text
Kokkinos_Ubernet_Training_a_CVPR_2017_paper.pdf - Published Version

Download (1MB) | Preview

Abstract

In this work we train in an end-to-end manner a convolutional neural network (CNN) that jointly handles low-, mid-, and high-level vision tasks in a unified architecture. Such a network can act like a swiss knife for vision tasks, we call it an UberNet to indicate its overarching nature. The main contribution of this work consists in handling challenges that emerge when scaling up to many tasks. We introduce techniques that facilitate (i) training a deep architecture while relying on diverse training sets and (ii) training many (potentially unlimited) tasks with a limited memory budget. This allows us to train in an end-to-end manner a unified CNN architecture that jointly handles (a) boundary detection (b) normal estimation (c) saliency estimation (d) semantic segmentation (e) human part segmentation (f) semantic boundary detection, (g) region proposal generation and object detection. We obtain competitive performance while jointly addressing all tasks in 0.7 seconds on a GPU. Our system will be made publicly available.

Type: Proceedings paper
Title: UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory
Event: 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Location: Honolulu, HI
Dates: 21 July 2017 - 26 July 2017
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/CVPR.2017.579
Publisher version: https://doi.org/10.1109/CVPR.2017.579
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: Science & Technology, Technology, Computer Science, Artificial Intelligence, Computer Science, Theory & Methods, Engineering, Electrical & Electronic, Computer Science, Engineering
UCL classification: UCL
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/10060980
Downloads since deposit
99Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item