Exploring loss functions for optimising the accuracy of Siamese neural networks in re-identification applications

4 March 2022 Exploring loss functions for optimising the accuracy of Siamese neural networks in re-identification applications

Jonathan Eichild Schmidt, Oscar Edvard Mäkinen, Simon Gørtz Flou Nielsen, Anders Skaarup Johansen, Kamal Nasrollahi, Thomas B. Moeslund

Author Affiliations +

Proceedings Volume 12084, Fourteenth International Conference on Machine Vision (ICMV 2021); 120840W (2022) https://doi.org/10.1117/12.2622634
Event: Fourteenth International Conference on Machine Vision (ICMV 2021), 2021, Rome, Italy

Abstract

Re-Identification (Re-ID) is becoming more and more common in today’s world, the need for more optimized algorithms also becomes more wanted. This is due to the importance of high accuracy as the consequences of an incorrect match can mean security issues, if used to gain access or result in incorrect findings in science due to wrong data. This paper explores enhancing the performance of Siamese Neural Networks by exploring the performance of loss functions to better suit the user’s Re-IDing needs. These loss functions are Triplet loss, Triplet Hard loss and Quadruplet loss. Results show that the Triplet hard loss function performs better than the two others. The functions were tested on a human dataset as well as on animal datasets.

Citation Download Citation

Jonathan Eichild Schmidt, Oscar Edvard Mäkinen, Simon Gørtz Flou Nielsen, Anders Skaarup Johansen, Kamal Nasrollahi, and Thomas B. Moeslund "Exploring loss functions for optimising the accuracy of Siamese neural networks in re-identification applications", Proc. SPIE 12084, Fourteenth International Conference on Machine Vision (ICMV 2021), 120840W (4 March 2022); https://doi.org/10.1117/12.2622634