Transcription of DeepFace: Closing the Gap to Human-Level Performance in ...
{{id}} {{{paragraph}}}
Example: marketing
DeepFace: Closing the Gap to Human-Level Performance in ...
DeepFace: Closing the Gap to Human-Level Performance in Face VerificationYaniv TaigmanMing YangMarc Aurelio RanzatoFacebook AI ResearchMenlo Park, CA, USA{yaniv, mingyang, WolfTel Aviv UniversityTel Aviv, modern face recognition, the conventional pipelineconsists of four stages: detect align represent clas-sify. We revisit both the alignment step and the representa-tion step by employing explicit 3D face modeling in order toapply a piecewise affine transformation, and derive a facerepresentation from a nine-layer deep neural network. Thisdeep network involves more than 120 million parametersusing several locally connected layers without weight shar-ing, rather than the standard convolutional layers.}
3D Alignment In order to align faces undergoing out-of-plane rotations, we use a generic 3D shape model and register a 3D affine camera, which are used to warp the 2D-aligned crop to the image plane of the 3D shape. This gen-erates the 3D-aligned version of the crop as illustrated in Fig.1(g). This is achieved by localizing additional 67 fidu-
Loading..
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: