Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A Step Towards Explainable Person Re-identification Rankings

: Specker, Andreas

Fulltext urn:nbn:de:0011-n-6383763 (1.3 MByte PDF)
MD5 Fingerprint: 3e3aa917fb39afe56193a1ca61319d66
(CC) by
Created on: 29.7.2021

Beyerer, Jürgen (Ed.); Zander, Tim (Ed.):
Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory 2020. Proceedings : 27th to the 31st of July 2020, Karlsruhe
Karlsruhe: KIT Scientific Publishing, 2021 (Karlsruher Schriften zur Anthropomatik 51)
ISBN: 978-3-7315-1091-8
DOI: 10.5445/KSP/1000130397
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation and Institute for Anthropomatics, Vision and Fusion Laboratory (Joint Workshop) <2020, Karlsruhe>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

More and more video and image data is available to security authorities that can help solve crimes. Since manual analysis is time-consuming, algorithms are needed that support e.g. re-identification of persons. However, person re-identification approaches solely output image rank lists but do not provide an explanation for the results. In this work, two concepts are proposed to explain person re-identification rankings and a qualitative evaluation is conducted. Both approaches are based on a multi-task convolutional neural network which outputs feature vectors for person re-identification and simultaneously recognizes a person’s semantic attributes. Analyses of the learned weights and the outputs of the attribute classifier are used to generate the explanations. The results of the conducted experiments indicate that both approaches are suitable to improve the comprehensibility of person re-identification rankings.