Graph-based Particular Object Discovery - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Machine Vision and Applications Year : 2019

Graph-based Particular Object Discovery


Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, that are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discriminative and common in the dataset. Saliency is based on a central-ity measure of a nearest neighbor graph constructed from regional CNN representations of dataset images. The proposed method exploits recent CNN architectures trained for object retrieval to construct the image representation from the salient regions. We improve particular object retrieval on challenging datasets containing small objects.
Fichier principal
Vignette du fichier
J28.mva18.disco.pdf (4.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02370238 , version 1 (19-11-2019)



Oriane Siméoni, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum. Graph-based Particular Object Discovery. Machine Vision and Applications, 2019, 30 (2), pp.243-254. ⟨10.1007/s00138-019-01005-z⟩. ⟨hal-02370238⟩
78 View
211 Download



Gmail Facebook X LinkedIn More