Twin identification over viewpoint change: A deep convolutional neural network surpasses humans

Autor: Parde, Connor J., Strehle, Virginia E., Banerjee, Vivekjyoti, Hu, Ying, Cavazos, Jacqueline G., Castillo, Carlos D., O'Toole, Alice J.

Deep convolutional neural networks (DCNNs) have achieved human-level accuracy in face identification (Phillips et al., 2018), though it is unclear how accurately they discriminate highly-similar faces. Here, humans and a DCNN performed a challenging

Externí odkaz: http://arxiv.org/abs/2207.05316

Deep convolutional neural networks are sensitive to face configuration.

Autor: Strehle VE; School of Behavioral and Brain Sciences, The University of Texas at Dallas, Dallas, Texas, USA.; https://orcid.org/0000-0002-0317-049X.; ginni.strehle@utdallas.edu., Bendiksen NK; School of Behavioral and Brain Sciences, The University of Texas at Dallas, Dallas, Texas, USA.; https://orcid.org/0009-0005-6596-2440.; natalie@utdallas.edu., O'Toole AJ; School of Behavioral and Brain Sciences, The University of Texas at Dallas, Dallas, Texas, USA.; https://orcid.org/0000-0001-7981-1508.; otoole@utdallas.edu.

Publikováno v: Journal of vision [J Vis] 2024 Nov 04; Vol. 24 (12), pp. 6.