VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognition

11 Oct 2019Mengjia YanMengao ZhaoZining XuQian ZhangGuoli WangZhizhong Su

To improve the discriminative and generalization ability of lightweight network for face recognition, we propose an efficient variable group convolutional network called VarGFaceNet. Variable group convolution is introduced by VarGNet to solve the conflict between small computational cost and the unbalance of computational intensity inside a block... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Face Verification AgeDB-30 VarGFaceNet Accuracy 0.9815 # 1
Face Verification CFP-FP VarGFaceNet Accuracy 0.985 # 1
Face Verification Labeled Faces in the Wild VarGFaceNet Accuracy 99.85% # 1

Methods used in the Paper