![]() |
|||||||||||||||
![]() |
Cerca | Lliura | Ajuda | Servei de Biblioteques | Sobre el DDD | Català English Español |
Pàgina inicial > Contribucions a jornades i congressos > Ponències i comunicacions > Metric learning for novelty and anomaly detection |
Data: | 2019 |
Resum: | When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so too confidently. The capability to detect out-of-distribution images is therefore crucial for many real-world applications. We divide out-of-distribution detection between novelty detection -images of classes which are not in the training set but are related to those-, and anomaly detection -images with classes which are unrelated to the training set. By related we mean they contain the same type of objects, like digits in MNIST and SVHN. Most existing work has focused on anomaly detection, and has addressed this problem considering networks trained with the cross-entropy loss. Differently from them, we propose to use metric learning which does not have the drawback of the softmax layer (inherent to cross-entropy methods), which forces the network to divide its prediction power over the learned classes. We perform extensive experiments and evaluate both novelty and anomaly detection, even in a relevant application such as traffic sign recognition, obtaining comparable or better results than previous works. |
Ajuts: | European Commission 777720 Agencia Estatal de Investigación TIN2017-88709-R Agencia Estatal de Investigación TIN2016-79717-R Ministerio de Economía y Competitividad PCIN-2015-251 Agència de Gestió d'Ajuts Universitaris i de Recerca 2018/FI_B1-00198 |
Nota: | Altres ajuts: we also acknowledge the CERCA Programme of Generalitat de Catalunya and its ACCIO agency. |
Drets: | Aquest material està protegit per drets d’autor i/o drets afins. Podeu utilitzar aquest material en funció del que permet la legislació de drets d’autor i drets afins d'aplicació al vostre cas. Per a d’altres usos heu d’obtenir permís del(s) titular(s) de drets. |
Llengua: | Anglès |
Document: | Comunicació de congrés ; recerca ; Versió acceptada per publicar |
Publicat a: | British Machine Vision Conference. Northumbria University (Newcastle), 3-6 Sep. 2018 |
Postprint 18 p, 4.7 MB |