TY  - CONF
AU  - Parichehr Behjati Ardakani
AU  - Diego Velazquez
AU  - Josep M. Gonfaus
AU  - Pau Rodriguez
AU  - Xavier Roca
AU  - Jordi Gonzalez
A2  - IbPRIA
PY  - 2019//
TI  - Catastrophic interference in Disguised Face Recognition
T2  - LNCS
BT  - 9th Iberian Conference on Pattern Recognition and Image Analysis
SP  - 64
EP  - 75
VL  - 11868
KW  - Neural network forgetness
KW  - Face recognition
KW  - Disguised Faces
N2  - 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.
L1  - http://refbase.cvc.uab.es/files/AVG2019.pdf
UR  - http://dx.doi.org/10.1007/978-3-030-31321-0_6
N1  - ISE; 600.098; 600.119
ID  - Parichehr Behjati Ardakani2019
ER  -