Détail de l'auteur
Auteur Andreas Veit |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Titre : Convolutional networks with adaptive inference graphs Type de document : Article/Communication Auteurs : Andreas Veit, Auteur ; Serge Belongie, Auteur Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2018 Collection : Lecture notes in Computer Science, ISSN 0302-9743 num. 11205 Conférence : ECCV 2018, 15th European Conference 08/09/2018 14/09/2018 Munich Allemagne Proceedings Springer Importance : pp 3 - 18 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] graphe
[Termes IGN] inférence
[Termes IGN] réseau neuronal convolutifRésumé : (auteur) Do convolutional networks really need a fixed feed-forward structure? What if, after identifying the high-level concept of an image, a network could move directly to a layer that can distinguish fine-grained differences? Currently, a network would first need to execute sometimes hundreds of intermediate layers that specialize in unrelated aspects. Ideally, the more a network already knows about an image, the better it should be at deciding which layer to compute next. In this work, we propose convolutional networks with adaptive inference graphs (ConvNet-AIG) that adaptively define their network topology conditioned on the input image. Following a high-level structure similar to residual networks (ResNets), ConvNet-AIG decides for each input image on the fly which layers are needed. In experiments on ImageNet, we show that ConvNet-AIG learns distinct inference graphs for different categories. Both ConvNet-AIG with 50 and 101 layers outperform their ResNet counterpart, while using 20% and 33% less computations respectively. By grouping parameters into layers for related classes and only executing relevant layers, ConvNet-AIG improves both efficiency and overall classification quality. Lastly, we also study the effect of adaptive inference graphs on the susceptibility towards adversarial examples. We observe that ConvNet-AIG shows a higher robustness than ResNets, complementing other known defense mechanisms. Numéro de notice : C2018-128 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Communication DOI : 10.1007/978-3-030-01246-5_1 En ligne : http://dx.doi.org/10.1007/978-3-030-01246-5_1 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100058