University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance

Spencer, Jaime, Bowden, Richard and Hadfield, Simon (2020) Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance In: CVPR 2020, 2020-06-14-2020-06-19, Seattle, Washington.

[img]
Preview
Text
dejavu_features.pdf - Accepted version Manuscript

Download (8MB) | Preview

Abstract

“Like night and day” is a commonly used expression to imply that two things are completely different. Unfortunately, this tends to be the case for current visual feature representations of the same scene across varying seasons or times of day. The aim of this paper is to provide a dense feature representation that can be used to perform localization, sparse matching or image retrieval,regardless of the current seasonal or temporal appearance. Recently, there have been several proposed methodologies for deep learning dense feature representations. These methods make use of ground truth pixel-wise correspondences between pairs of images and focus on the spatial properties of the features. As such, they don’t address temporal or seasonal variation. Furthermore, obtaining the required pixel-wise correspondence data to train in cross-seasonal environments is highly complex in most scenarios. We propose Deja-Vu, a weakly supervised approach to learning season invariant features that does not require pixel-wise ground truth data. The proposed system only requires coarse labels indicating if two images correspond to the same location or not. From these labels, the network is trained to produce “similar” dense feature maps for corresponding locations despite environmental changes. Code will be made available at: https://github.com/ jspenmar/DejaVu_Features

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
NameEmailORCID
Spencer, Jaimejaime.spencer@surrey.ac.uk
Bowden, RichardR.Bowden@surrey.ac.uk
Hadfield, Simons.hadfield@surrey.ac.uk
Date : 26 February 2020
Funders : EPSRC - Engineering and Physical Sciences Research Council
Copyright Disclaimer : © 2020 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 :
Additional Information : Paper ID - 303. This work was funded by the EPSRC under grant agreement (EP/R512217/1). We would also like to thank NVIDIA Corporation for their Titan Xp GPU grant.
Depositing User : Diane Maxfield
Date Deposited : 21 Apr 2020 15:08
Last Modified : 16 Jun 2020 02:08
URI: http://epubs.surrey.ac.uk/id/eprint/854154

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