University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation

Spencer, Jaime, Bowden, Richard and Hadfield, Simon (2019) Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 16-20 Jun 2019, Long Beach, California, USA.

[img]
Preview
Text
Scale-Adaptive Neural Dense Features.pdf - Accepted version Manuscript

Download (9MB) | Preview

Abstract

How do computers and intelligent agents view the world around them? Feature extraction and representation constitutes one the basic building blocks towards answering this question. Traditionally, this has been done with carefully engineered hand-crafted techniques such as HOG, SIFT or ORB. However, there is no “one size fits all” approach that satisfies all requirements.

In recent years, the rising popularity of deep learning has resulted in a myriad of end-to-end solutions to many computer vision problems. These approaches, while successful, tend to lack scalability and can’t easily exploit information learned by other systems.

Instead, we propose SAND features, a dedicated deep learning solution to feature extraction capable of providing hierarchical context information. This is achieved by employing sparse relative labels indicating relationships of similarity/dissimilarity between image locations. The nature of these labels results in an almost infinite set of dissimilar examples to choose from. We demonstrate how the selection of negative examples during training can be used to modify the feature space and vary it’s properties.

To demonstrate the generality of this approach, we apply the proposed features to a multitude of tasks, each requiring different properties. This includes disparity estimation, semantic segmentation, self-localisation and SLAM. In all cases, we show how incorporating SAND features results in better or comparable results to the baseline, whilst requiring little to no additional training. Code can be found at: https://github.com/jspenmar/SAND_features

Item Type: Conference or Workshop Item (Conference Poster)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Spencer, Jaimejaime.spencer@surrey.ac.uk
Bowden, RichardR.Bowden@surrey.ac.uk
Hadfield, Simons.hadfield@surrey.ac.uk
Date : 16 June 2019
Copyright Disclaimer : © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Related URLs :
Depositing User : Clive Harris
Date Deposited : 28 Mar 2019 08:28
Last Modified : 16 Jun 2019 02:08
URI: http://epubs.surrey.ac.uk/id/eprint/850894

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800