Semantic Based Adversarial Examples Fool Face Recognition
Researchers have proposed a new adversarial attack approach, SemanticAdv, which generates adversarial perturbations by manipulating not pixels but rather an image’s semantic attributes.
Tag: face recognition
2018 in Review: 10 AI Failures
Last December Synced compiled its first “Artificial Intelligence Failures” recap of AI gaffes from the previous year. AI has achieved remarkable progress, and many scientists dream of creating the Master Algorithm proposed by Pedro Domingos — which can solve all problems envisioned by humans.
Computer Vision Startup CloudWalk Collects US$375 Million
Heavy investments in computer vision will energize the IoT revolution that is rapidly building smart city infrastructures all across Asia.
L2-constrained Softmax Loss for Discriminative Face Verification
Softmax loss has become a standard build-in loss function for a lot of mathematical tools like TensorFlow, Torch and Caffe. It is mainly used for classification and has its advantages and disadvantages, the latter of which is the focus of this paper.
Face Aging with Conditional Generative Adversarial Networks
The main advantage of the acGAN is the “Identity-Preserving” latent vector optimization approach to maintain the original person’s identity in reconstruction.