Home » Publication » 18581

Dettaglio pubblicazione

2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Pages 2100-2109

When Naïve bayes nearest neighbors meet convolutional neural networks (04b Atto di convegno in volume)

Kuzborskij Ilja, Carlucci FABIO MARIA, Caputo Barbara

Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbor (NBNN)-based classifiers have lost momentum in the community. This is because (1) such algorithms cannot use CNN activations as input features, (2) they cannot be used as final layer of CNN architectures for end-to-end training, and (3) they are generally not scalable and hence cannot handle big data. This paper proposes a framework that addresses all these issues, thus bringing back NBNNs on the map. We solve the first by extracting CNN activations from local patches at multiple scale levels, similarly to [13]. We address simultaneously the second and third by proposing a scalable version of Naive Bayes Non-linear Learning (NBNL, [7]). Results obtained using pre-trained CNNs on standard scene and domain adaptation databases show the strength of our approach, opening a new season for NBNNs. © 2016 IEEE.
ISBN: 9781467388511
keywords
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma