4 papers
Beyond cross-entropy: learning highly separable feature distributions for robust and accurate classification
Arslan Ali, Andrea Migliorati, Tiziano Bianchi +1
Deep learning has shown outstanding performance in several applications including image classification. However, deep classifiers are known to be highly vulnerable to adversarial a…
BioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions
Arslan Ali, Matteo Testa, Tiziano Bianchi +1
We present BioMetricNet: a novel framework for deep unconstrained face verification which learns a regularized metric to compare facial features. Differently from popular methods s…
Learning mappings onto regularized latent spaces for biometric authentication
Matteo Testa, Arslan Ali, Tiziano Bianchi +1
We propose a novel architecture for generic biometric authentication based on deep neural networks: RegNet. Differently from other methods, RegNet learns a mapping of the input bio…
Analysis of SparseHash: an efficient embedding of set-similarity via sparse projections
Diego Valsesia, Sophie Marie Fosson, Chiara Ravazzi +2
Embeddings provide compact representations of signals in order to perform efficient inference in a wide variety of tasks. In particular, random projections are common tools to cons…