Analysing domain shift factors between videos and images for object detection

Vicky Kalogeiton 1, 2 Vittorio Ferrari 1 Cordelia Schmid 2
1 CALVIN research group [Edinburgh]
IPAB - Institute of Perception, Action and Behaviour
2 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : Object detection is one of the most important challenges in computer vision. Object detectors are usually trained on bounding-boxes from still images. Recently, video has been used as an alternative source of data. Yet, for a given test domain (image or video), the performance of the detector depends on the domain it was trained on. In this paper, we examine the reasons behind this performance gap. We define and evaluate different domain shift factors: spatial location accuracy, appearance diversity, image quality and aspect distribution. We examine the impact of these factors by comparing performance before and after factoring them out. The results show that all four factors affect the performance of the detectors and their combined effect explains nearly the whole performance gap.
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2016, 38 (11), pp.2327-2334. <10.1109/TPAMI.2016.2551239>
Liste complète des métadonnées


https://hal.inria.fr/hal-01281069
Contributeur : Thoth Team <>
Soumis le : mardi 31 mai 2016 - 15:24:30
Dernière modification le : vendredi 17 février 2017 - 16:13:38
Document(s) archivé(s) le : jeudi 1 septembre 2016 - 12:35:10

Fichier

vicky_pami2016.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Vicky Kalogeiton, Vittorio Ferrari, Cordelia Schmid. Analysing domain shift factors between videos and images for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2016, 38 (11), pp.2327-2334. <10.1109/TPAMI.2016.2551239>. <hal-01281069v2>

Partager

Métriques

Consultations de
la notice

544

Téléchargements du document

280