BPLF: A Bi-Parallel Linear Flow Model for Facial Expression Generation from Emotion Set Images
This work addresses facial expression generation for emotion analysis applications, but it appears incremental as it builds on existing flow-based models with specific optimizations.
The authors tackled the problem of generating facial expressions from emotion set images by constructing a bi-parallel linear flow model, which improved expression ability and convergence speed, with experiments showing that 3-layer 3*3 convolutions and principal component decomposition enhanced feature extraction and training efficiency.
The flow-based generative model is a deep learning generative model, which obtains the ability to generate data by explicitly learning the data distribution. Theoretically its ability to restore data is stronger than other generative models. However, its implementation has many limitations, including limited model design, too many model parameters and tedious calculation. In this paper, a bi-parallel linear flow model for facial emotion generation from emotion set images is constructed, and a series of improvements have been made in terms of the expression ability of the model and the convergence speed in training. The model is mainly composed of several coupling layers superimposed to form a multi-scale structure, in which each coupling layer contains 1*1 reversible convolution and linear operation modules. Furthermore, this paper sorted out the current public data set of facial emotion images, made a new emotion data, and verified the model through this data set. The experimental results show that, under the traditional convolutional neural network, the 3-layer 3*3 convolution kernel is more conducive to extracte the features of the face images. The introduction of principal component decomposition can improve the convergence speed of the model.