GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations

The development of deep learning-based biometric models that can be deployed on devices with constrained memory and computational resources has proven to be a significant challenge. Previous approaches to this problem have not prioritized the reduction of feature map redundancy, but the introduction of Ghost modules represents a major innovation in this area. Ghost modules use a series of inexpensive linear transformations to extract additional feature maps from a set of intrinsic features, allowing for a more comprehensive representation of the underlying information. GhostNetV1 and GhostNetV2, both of which are based on Ghost modules, serve as the foundation for a group of lightweight face recognition models called GhostFaceNets. GhostNetV2 expands upon the original GhostNetV1 by adding an attention mechanism to capture long-range dependencies. Evaluation of GhostFaceNets using various benchmarks reveals that these models offer superior performance while requiring a computational complexity of approximately 60–275 MFLOPs. This is significantly lower than that of State-Of-The-Art (SOTA) big convolutional neural network (CNN) models, which can require hundreds of millions of FLOPs. GhostFaceNets trained with the ArcFace loss on the refined MS-Celeb-1M dataset demonstrate SOTA performance on all benchmarks. In comparison to previous SOTA mobile CNNs, GhostFaceNets greatly improve efficiency for face verification tasks. The GhostFaceNets code is available at: .

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Face Verification AgeDB-30 GhostFaceNetV2-1 Accuracy 0.9862 # 2
Face Recognition CALFW GhostFaceNetV2-1 Accuracy 0.9612 # 3
Face Recognition CFP-FF GhostFaceNetV2-1 Accuracy 99.9143 # 1
Face Recognition CFP-FP GhostFaceNetV2-1 Accuracy 0.9933 # 1
Face Recognition CPLFW GhostFaceNetV2-1 Accuracy 0.9465 # 1
Face Recognition LFW GhostFaceNetV2-1 (MS1MV3) Accuracy 0.998667 # 1
Face Verification MegaFace GhostFaceNetV2-1 Accuracy 98.72% # 3
Face Identification MegaFace GhostFaceNetV2-1 Accuracy 98.64% # 5