Centre de documentation
scientifique

Discriminative information restoration and extraction for weakly supervised low-resolution fine-grained image recognition / Tiantian Yan in Pattern recognition, vol 127 (July 2022)  

Public [article]  inPattern recognition > vol 127 (July 2022) . - n° 108629 Titre : Discriminative information restoration and extraction for weakly supervised low-resolution fine-grained image recognition Type de document : Article/Communication Auteurs : Tiantian Yan, Auteur ; Jian Shi, Auteur ; Haojie Li, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 108629 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse discriminante [Termes IGN] arbre aléatoire minimum [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] extraction de données [Termes IGN] granularité d'image [Termes IGN] image à basse résolution [Termes IGN] image à haute résolution [Termes IGN] relation sémantique [Termes IGN] texture d'image Résumé : (auteur) The existing methods of fine-grained image recognition mainly devote to learning subtle yet discriminative features from the high-resolution input. However, their performance deteriorates significantly when they are used for low quality images because a lot of discriminative details of images are missing. We propose a discriminative information restoration and extraction network, termed as DRE-Net, to address the problem of low-resolution fine-grained image recognition, which has widespread application potential, such as shelf auditing and surveillance scenarios. DRE-Net is the first framework for weakly supervised low-resolution fine-grained image recognition and consists of two sub-networks: (1) fine-grained discriminative information restoration sub-network (FDR) and (2) recognition sub-network with the semantic relation distillation loss (SRD-loss). The first module utilizes the structural characteristic of minimum spanning tree (MST) to establish context information for each pixel by employing the spatial structures between each pixel and other pixels, which can help FDR focus on and restore the critical texture details. The second module employs the SRD-loss to calibrate recognition sub-network by transferring the correct relationships between every two pixels on the feature map. Meanwhile the SRD-loss can further prompt the FDR to recover reliable and accurate fine-grained details and guide the recognition sub-network to perceive the discriminative features from the correct relationships. Extensive experiments on three benchmark datasets and one retail product dataset demonstrate the effectiveness of our proposed framework. Numéro de notice : A2022-555 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.patcog.2022.108629 Date de publication en ligne : 06/03/2022 En ligne : https://doi.org/10.1016/j.patcog.2022.108629 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101168 [article]