Continual Learning for Image-Based Camera Localization

Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov, Xiaotian Li, Juho Kannala

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

8 Downloads (Pure)

Abstract

For several emerging technologies such as augmented reality, autonomous driving and robotics, visual localization is a critical component. Directly regressing camera pose/3D scene coordinates from the input image using deep neural networks has shown great potential. However, such methods assume a stationary data distribution with all scenes simultaneously available during training. In this paper, we approach the problem of visual localization in a continual learning setup -- whereby the model is trained on scenes in an incremental manner. Our results show that similar to the classification domain, non-stationary data induces catastrophic forgetting in deep networks for visual localization. To address this issue, a strong baseline based on storing and replaying images from a fixed buffer is proposed. Furthermore, we propose a new sampling method based on coverage score (Buff-CS) that adapts the existing sampling strategies in the buffering process to the problem of visual localization. Results demonstrate consistent improvements over standard buffering methods on two challenging datasets -- 7Scenes, 12Scenes, and also 19Scenes by combining the former scenes.
Original languageEnglish
Title of host publication2021 International Conference on Computer Vision, ICCV
PublisherIEEE
Pages3232-3242
Number of pages11
ISBN (Electronic)978-1-6654-2812-5
ISBN (Print)978-1-6654-2813-2
DOIs
Publication statusPublished - 2022
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Computer Vision - Virtual, Online
Duration: 11 Oct 202117 Oct 2021

Publication series

NameIEEE International Conference on Computer Vision
PublisherIEEE
ISSN (Print)1550-5499
ISSN (Electronic)2380-7504

Conference

ConferenceInternational Conference on Computer Vision
Abbreviated titleICCV
CityVirtual, Online
Period11/10/202117/10/2021

Fingerprint

Dive into the research topics of 'Continual Learning for Image-Based Camera Localization'. Together they form a unique fingerprint.

Cite this