FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method
This addresses the need for efficient gender classification on devices with limited networking and computing, though it is an incremental improvement building on PixelHop++.
The paper tackles the problem of face gender classification in resource-constrained environments by proposing FaceHop, a light-weight method that achieves correct classification rates of 94.63% and 95.12% on low-resolution images with model sizes of 16.9K and 17.6K parameters, outperforming LeNet-5.
A light-weight low-resolution face gender classification method, called FaceHop, is proposed in this research. We have witnessed rapid progress in face gender classification accuracy due to the adoption of deep learning (DL) technology. Yet, DL-based systems are not suitable for resource-constrained environments with limited networking and computing. FaceHop offers an interpretable non-parametric machine learning solution. It has desired characteristics such as a small model size, a small training data amount, low training complexity, and low-resolution input images. FaceHop is developed with the successive subspace learning (SSL) principle and built upon the foundation of PixelHop++. The effectiveness of the FaceHop method is demonstrated by experiments. For gray-scale face images of resolution $32 \times 32$ in the LFW and the CMU Multi-PIE datasets, FaceHop achieves correct gender classification rates of 94.63% and 95.12% with model sizes of 16.9K and 17.6K parameters, respectively. It outperforms LeNet-5 in classification accuracy while LeNet-5 has a model size of 75.8K parameters.