Centre de documentation
scientifique

Deep filter banks for texture recognition, description, and segmentation / Mircea Cimpoi in International journal of computer vision, vol 118 n° 1 (May 2016)  

Public [article]  inInternational journal of computer vision > vol 118 n° 1 (May 2016) . - pp 65 – 94 Titre : Deep filter banks for texture recognition, description, and segmentation Type de document : Article/Communication Auteurs : Mircea Cimpoi, Auteur ; Subhransu Maji, Auteur ; Iasonas Kokkinos, Auteur ; Andrea Vedaldi, Auteur Année de publication : 2016 Article en page(s) : pp 65 – 94 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] accès aux données [Termes IGN] apprentissage profond [Termes IGN] attribut sémantique [Termes IGN] filtrage numérique d'image [Termes IGN] jeu de données [Termes IGN] segmentation d'image [Termes IGN] texture d'image Résumé : (auteur) Visual textures have played a key role in image understanding because they convey important semantics of images, and because texture representations that pool local image descriptors in an orderless manner have had a tremendous impact in diverse applications. In this paper, we make several contributions to texture understanding. First, instead of focusing on texture instance and material category recognition, we propose a human-interpretable vocabulary of texture attributes to describe common texture patterns, complemented by a new describable texture dataset for benchmarking. Second, we look at the problem of recognizing materials and texture attributes in realistic imaging conditions, including when textures appear in clutter, developing corresponding benchmarks on top of the recently proposed OpenSurfaces dataset. Third, we revisit classic texture representations, including bag-of-visual-words and the Fisher vectors, in the context of deep learning and show that these have excellent efficiency and generalization properties if the convolutional layers of a deep model are used as filter banks. We obtain in this manner state-of-the-art performance in numerous datasets well beyond textures, an efficient method to apply deep features to image regions, as well as benefit in transferring features from one domain to another. Numéro de notice : A2016--151 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007%2Fs11263-015-0872-3 En ligne : https://doi.org/10.1007/s11263-015-0872-3 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85919 [article]