Скачать или смотреть "Deep Learning Based One-Class Detection System for Fake Faces Generated by GAN Network", (2022).

◆Title
"Deep Learning Based One-Class Detection System for Fake Faces Generated by GAN Network", Sensors, 22(20): 7767 (24pages), (2022.10.13).
◆Explanation
((Subject/Topic)) Fake face detection
((Purpose/Aim)) Fake face detection.
((Approach/Idea)) Generative Adversarial Network (GAN)
((Result))
This is one of the results of joint research between Warsaw University of Technology (Dr. Vibekananda Dutta) and Waseda University (Prof. Takafumi Matsumaru). Details are shown on the following paper(s):
Shengyin Li, Vibekananda Dutta, Xin He, Takafumi Matsumaru: "Deep Learning Based One-Class Detection System for Fake Faces Generated by GAN Network", Sensors (MDPI), 22(20): 7767 (24pages), (2022.10.13), doi:10.3390/s22207767.
https://www.mdpi.com/1424-8220/22/20/...
((Date)) 2022.10.13.
((Copyright)) Bio-Robotics and Human-Mechatronics Laboratory (BRHM lab) (Takafumi Matsumaru Laboratory), Graduate School of Information, Production and Systems (IPS), Waseda University.
https://sem-matsumaru.w.waseda.jp/
https://matsumaru.w.waseda.jp/
((Keywords)) Multi-Channel Convolutional Neural Network (MCCNN), face anti-spoofing, attention learning, self-attention, data augmentation, deep learning, Generative Adversarial Network (GAN), Weakly Supervised Learning (WSL), Warsaw University of Technology, Waseda University,