Supervised Fine-tuning Evaluation for Long-term Visual Place Recognition

Farid Alijani, Esa Rahtu

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


In this paper, we present a comprehensive study on the utility of deep convolutional neural networks with two state-of-the-art pooling layers which are placed after convolutional layers and fine-tuned in an end-to-end manner for visual place recognition task in challenging conditions, including seasonal and illumination variations. We compared extensively the performance of deep learned global features with three different loss functions, e.g. triplet, contrastive and ArcFace, for learning the parameters of the architectures in terms of fraction of the correct matches during deployment. To verify effectiveness of our results, we utilized two real world datasets in place recognition, both indoor and outdoor. Our investigation demonstrates that fine tuning architectures with ArcFace loss in an end-to-end manner outperforms other two losses by approximately 1 ~ 4 % in outdoor and 1 ~ 2 % in indoor datasets, given certain thresholds, for the visual place recognition tasks.

Original languageEnglish
Title of host publicationIEEE 23rd International Workshop on Multimedia Signal Processing, MMSP 2021
Number of pages6
ISBN (Electronic)9781665432870
Publication statusPublished - 2022
Publication typeA4 Article in conference proceedings
EventIEEE International Workshop on Multimedia Signal Processing - Tampere, Finland
Duration: 6 Oct 20218 Oct 2021

Publication series

NameIEEE International Workshop on Multimedia Signal Processing
ISSN (Electronic)2473-3628


ConferenceIEEE International Workshop on Multimedia Signal Processing
Abbreviated titleIEEE MMSP 2021
Internet address

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Signal Processing
  • Safety, Risk, Reliability and Quality
  • Media Technology


Dive into the research topics of 'Supervised Fine-tuning Evaluation for Long-term Visual Place Recognition'. Together they form a unique fingerprint.

Cite this