no code implementations • 12 Jul 2022 • Connor J. Parde, Virginia E. Strehle, Vivekjyoti Banerjee, Ying Hu, Jacqueline G. Cavazos, Carlos D. Castillo, Alice J. O'Toole
These findings also contribute to our understanding of DCNN performance for discriminating high-resemblance faces, demonstrate that the DCNN performs at a level at or above humans, and suggest a degree of parity between the features used by humans and the DCNN.
no code implementations • 26 Apr 2022 • Snipta Mallick, Geraldine Jeckeln, Connor J. Parde, Carlos D. Castillo, Alice J. O'Toole
Similar to humans, the DCNN performed more accurately for original face images than for morphed image pairs.
no code implementations • 14 Feb 2020 • Connor J. Parde, Y. Ivette Colón, Matthew Q. Hill, Carlos D. Castillo, Prithviraj Dhar, Alice J. O'Toole
Therefore, distributed and sparse codes co-exist in the network units to represent different face attributes.
no code implementations • 28 Dec 2018 • Matthew Q. Hill, Connor J. Parde, Carlos D. Castillo, Y. Ivette Colon, Rajeev Ranjan, Jun-Cheng Chen, Volker Blanz, Alice J. O'Toole
Deep convolutional neural networks (DCNNs) also create generalizable face representations, but with cascades of simulated neurons.
no code implementations • 6 Nov 2016 • Connor J. Parde, Carlos Castillo, Matthew Q. Hill, Y. Ivette Colon, Swami Sankaranarayanan, Jun-Cheng Chen, Alice J. O'Toole
The results show that the DCNN features contain surprisingly accurate information about the yaw and pitch of a face, and about whether the face came from a still image or a video frame.