Centre de documentation
scientifique

Effective triplet mining improves training of multi-scale pooled CNN for image retrieval / Federico Vaccaro in Machine Vision and Applications, vol 33 n° 1 (January 2022)  

Public [article]  inMachine Vision and Applications > vol 33 n° 1 (January 2022) . - n° 16 Titre : Effective triplet mining improves training of multi-scale pooled CNN for image retrieval Type de document : Article/Communication Auteurs : Federico Vaccaro, Auteur ; Marco Bertini, Auteur ; Tiberio Uricchio, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 16 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] agrégation de données [Termes IGN] analyse visuelle [Termes IGN] architecture de réseau [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] exploration de données [Termes IGN] extraction de traits caractéristiques [Termes IGN] recherche d'image basée sur le contenu [Termes IGN] réseau neuronal siamois [Termes IGN] triplet Résumé : (auteur) In this paper, we address the problem of content-based image retrieval (CBIR) by learning images representations based on the activations of a Convolutional Neural Network. We propose an end-to-end trainable network architecture that exploits a novel multi-scale local pooling based on the trainable aggregation layer NetVLAD (Arandjelovic et al in Proceedings of the IEEE conference on computer vision and pattern recognition CVPR, NetVLAD, 2016) and bags of local features obtained by splitting the activations, allowing to reduce the dimensionality of the descriptor and to increase the performance of retrieval. Training is performed using an improved triplet mining procedure that selects samples based on their difficulty to obtain an effective image representation, reducing the risk of overfitting and loss of generalization. Extensive experiments show that our approach, that can be effectively used with different CNN architectures, obtains state-of-the-art results on standard and challenging CBIR datasets. Numéro de notice : A2022-237 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00138-021-01260-z Date de publication en ligne : 06/01/2022 En ligne : https://doi.org/10.1007/s00138-021-01260-z Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100153 [article]