Seasonal domain shift in the global south: dataset and deep features analysis
conference contributionposted on 2023-06-19, 08:35 authored by Georgios VoulgarisGeorgios Voulgaris, Andy PhilippidesAndy Philippides, Jonathan DolleyJonathan Dolley, Jeremy ReffinJeremy Reffin, Fiona MarshallFiona Marshall, Novi QuadriantoNovi Quadrianto
Domain shifts during seasonal variations are an important aspect affecting the robustness of aerial scene classification and so it is crucial that such variation is captured within aerial scene datasets. This is more evident in geographic locations in the global South, where aerial coverage is scarcer and the rural and semi-urban landscape varies dramatically between wet and dry seasons. As current datasets do not offer the ability to experiment with domain shifts due to seasonal variations, this work proposes a labelled dataset for classifying land use from aerial images, comprising both wet and dry season data from Ghaziabad in India. Moreover, we conduct a thorough investigation into how image features, namely colour, shape, and texture, influence the accuracy of scene classification. We demonstrate that a combination of an architecture that extracts salient features, with the implementation of a larger receptive field improves classification performance when applied to both shallow or deep architectures by extracting invariant feature representations across domains.
- Accepted version
JournalConference on Computer Vision and Pattern Recognition (CVPR)
Event nameComputer Vision and Pattern Recognition (CVPR) EarthVision
Event locationVancouver, Canada
Event date18 June 2023
Department affiliated with
- Informatics Publications
Research groups affiliated with
- Sussex Sustainability Research Programme Publications
Notes© 2023 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.
Full text available