Centre de documentation
scientifique

Label propagation with ensemble of pairwise geometric relations : towards robust large-scale retrieval of object instances / Xiaomeng Wu in International journal of computer vision, vol 126 n° 7 (July 2018)  

Public [article]  inInternational journal of computer vision > vol 126 n° 7 (July 2018) . - pp 689 - 713 Titre : Label propagation with ensemble of pairwise geometric relations : towards robust large-scale retrieval of object instances Type de document : Article/Communication Auteurs : Xiaomeng Wu, Auteur ; Kaoru Hiramatsu, Auteur ; Kunio Kashino, Auteur Année de publication : 2018 Article en page(s) : pp 689 - 713 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] étiquette [Termes IGN] instance [Termes IGN] méthode robuste [Termes IGN] recherche d'image basée sur le contenu [Termes IGN] relation spatiale Résumé : (Auteur) Spatial verification methods permit geometrically stable image matching, but still involve a difficult trade-off between robustness as regards incorrect rejection of true correspondences and discriminative power in terms of mismatches. To address this issue, we ask whether an ensemble of weak geometric constraints that correlates with visual similarity only slightly better than a bag-of-visual-words model performs better than a single strong constraint. We consider a family of spatial verification methods and decompose them into fundamental constraints imposed on pairs of feature correspondences. Encompassing such constraints leads us to propose a new method, which takes the best of existing techniques and functions as a unified Ensemble of pAirwise GEometric Relations (EAGER), in terms of both spatial contexts and between-image transformations. We also introduce a novel and robust reranking method, in which the object instances localized by EAGER in high-ranked database images are reissued as new queries. EAGER is extended to develop a smoothness constraint where the similarity between the optimized ranking scores of two instances should be maximally consistent with their geometrically constrained similarity. Reranking is newly formulated as two label propagation problems: one is to assess the confidence of new queries and the other to aggregate new independently executed retrievals. Extensive experiments conducted on four datasets show that EAGER and our reranking method outperform most of their state-of-the-art counterparts, especially when large-scale visual vocabularies are used. Numéro de notice : A2018-411 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-018-1063-9 Date de publication en ligne : 31/01/2018 En ligne : https://doi.org/10.1007/s11263-018-1063-9 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90886 [article]