SqueezerFaceNet: Reducing a Small Face Recognition CNN Even More Via Filter Pruning
This addresses the need for efficient face recognition on mobile devices, but it is incremental as it builds on existing pruning methods applied to a new task.
The paper tackled the problem of large face recognition CNNs being impractical for mobile applications by developing SqueezerFaceNet, a network with less than 1M parameters, achieving up to 40% reduction in size from an already small base model without significant performance loss.
The widespread use of mobile devices for various digital services has created a need for reliable and real-time person authentication. In this context, facial recognition technologies have emerged as a dependable method for verifying users due to the prevalence of cameras in mobile devices and their integration into everyday applications. The rapid advancement of deep Convolutional Neural Networks (CNNs) has led to numerous face verification architectures. However, these models are often large and impractical for mobile applications, reaching sizes of hundreds of megabytes with millions of parameters. We address this issue by developing SqueezerFaceNet, a light face recognition network which less than 1M parameters. This is achieved by applying a network pruning method based on Taylor scores, where filters with small importance scores are removed iteratively. Starting from an already small network (of 1.24M) based on SqueezeNet, we show that it can be further reduced (up to 40%) without an appreciable loss in performance. To the best of our knowledge, we are the first to evaluate network pruning methods for the task of face recognition.