Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation


Low-resolution faces must be identified with minimal computational expense before face recognition algorithms may be used in the wild. Compressing a face model in order to increase speed and reduce memory consumption is a viable solution for this issue. This work presents a method for learning to detect low-resolution faces by selective knowledge distillation, inspired by that. Convolutional neural networks (CNNs) are used to recognise high-resolution and low-resolution faces with a teacher stream and a student stream, respectively, in this method. For high-accuracy recognition, the teacher stream is represented by a complicated CNN, whereas the student stream is represented by a much simpler CNN. As a result, we apply a sparse graph optimization problem to extract only the most relevant facial features from the instructor stream, which are then used to fine-tune the fine-tuning process of the student stream. Through the use of feature regression and low-resolution face classification to both approximate and recover the most informative facial cues, the student stream is actually trained to handle two jobs at once with limited computational resources in this manner. In tests, the student stream performs well in detecting low-resolution faces and consumes only 0.15 MB of memory and operates at 418 faces per second on CPU and 9433 faces per second on GPU.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE :(2N+1) Selective Harmonic Elimination-PWM for Modular Multilevel Converters: A Generalized Formulation and A Circulating Current Control Method - 2017ABSTRACT:The performance of modular multilevel converters (MMCs)
PROJECT TITLE : Scheduling for Workflows with Security-Sensitive Intermediate Data by Selective Tasks Duplication in Clouds - 2017 ABSTRACT: With the wide deployment of cloud computing in several business enterprises along
PROJECT TITLE :Selective gray-coded bit-plane based low-complexity motion estimation and its hardware architectureABSTRACT:Nowadays, many shopper electronics devices have video capturing capability which is one among the foremost
PROJECT TITLE :Selective Harmonic Elimination With Groebner Bases and Symmetric PolynomialsABSTRACT:Selective harmonic elimination (SHE) technology has been widely used in many medium- and high-power converters that operates at
PROJECT TITLE :Selective Stiffening for Producing a Mass-Fabrication Compatible Motion Conversion MechanismABSTRACT:We have a tendency to gift a mechanism that converts in-plane to out-of-plane motions, which is absolutely compatible

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry