PT Unknown
AU Parichehr Behjati Ardakani
   Diego Velazquez
   Josep M. Gonfaus
   Pau Rodriguez
   Xavier Roca
   Jordi Gonzalez
TI Catastrophic interference in Disguised Face Recognition
BT 9th Iberian Conference on Pattern Recognition and Image Analysis
PY 2019
BP 64
EP 75
VL 11868
DI 10.1007/978-3-030-31321-0_6
DE Neural network forgetness; Face recognition; Disguised Faces
AB 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.
ER