%0 Conference Proceedings
%T Catastrophic interference in Disguised Face Recognition
%A Parichehr Behjati Ardakani
%A Diego Velazquez
%A Josep M. Gonfaus
%A Pau Rodriguez
%A Xavier Roca
%A Jordi Gonzalez
%B 9th Iberian Conference on Pattern Recognition and Image Analysis
%D 2019
%V 11868
%F Parichehr Behjati Ardakani2019
%O ISE; 600.098; 600.119
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3416), last updated on Wed, 28 Sep 2022 09:39:13 +0200
%X It is commonly known the natural tendency of artificial neural networks to completely and abruptly forget previously known information when learning new information. We explore this behaviour in the context of Face Verification on the recently proposed Disguised Faces in the Wild dataset (DFW). We empirically evaluate several commonly used DCNN architectures on Face Recognition and distill some insights about the effect of sequential learning on distinct identities from different datasets, showing that the catastrophic forgetness phenomenon is present even in feature embeddings fine-tuned on different tasks from the original domain.
%K Neural network forgetness
%K Face recognition
%K Disguised Faces
%U http://refbase.cvc.uab.es/files/AVG2019.pdf
%U http://dx.doi.org/10.1007/978-3-030-31321-0_6
%P 64-75