Détail de l'auteur
Auteur Cheng-Lin Liu |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
SDE: A novel selective, discriminative and equalizing feature representation for visual recognition / Guo-Sen Xie in International journal of computer vision, vol 124 n° 2 (1 September 2017)
[article]
Titre : SDE: A novel selective, discriminative and equalizing feature representation for visual recognition Type de document : Article/Communication Auteurs : Guo-Sen Xie, Auteur ; Xu-Yao Zhang, Auteur ; Shuicheng Yan, Auteur ; Cheng-Lin Liu, Auteur Année de publication : 2017 Article en page(s) : pp pp 145 – 168 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage automatique
[Termes IGN] classification par réseau neuronal
[Termes IGN] optimisation (mathématiques)
[Termes IGN] reconnaissance d'objets
[Termes IGN] réseau neuronal convolutifRésumé : (auteur) Bag of Words (BoW) model and Convolutional Neural Network (CNN) are two milestones in visual recognition. Both BoW and CNN require a feature pooling operation for constructing the frameworks. Particularly, the max-pooling has been validated as an efficient and effective pooling method compared with other methods such as average pooling and stochastic pooling. In this paper, we first evaluate different pooling methods, and then propose a new feature pooling method termed as selective, discriminative and equalizing pooling (SDE). The SDE representation is a feature learning mechanism by jointly optimizing the pooled representations with the target of learning more selective, discriminative and equalizing features. We use bilevel optimization to solve the joint optimization problem. Experiments on seven benchmark datasets (including both single-label and multi-label ones) well validate the effectiveness of our framework. Particularly, we achieve the state-of-the-art fused results (mAP) of 93.21 and 93.97% on the PASCAL VOC2007 and VOC2012 datasets, respectively. Numéro de notice : A2017-482 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007%2Fs11263-017-1007-9 En ligne : https://doi.org/10.1007/s11263-017-1007-9 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86421
in International journal of computer vision > vol 124 n° 2 (1 September 2017) . - pp pp 145 – 168[article]