# BPLF: A Bi-Parallel Linear Flow Model for Facial Expression Generation from Emotion Set Images

arXiv: https://arxiv.org/abs/2106.07563 · HTML: https://mlsanity.com/paper/2106.07563/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 16 of 16)

- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design](https://mlsanity.com/paper/1902.00275/) (2019)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [JhatAA-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention](https://mlsanity.com/paper/2003.08834/) (2020)
- [Diversified Arbitrary Style Transfer via Deep Feature Perturbation](https://mlsanity.com/paper/1909.08223/) (2019)
- [Mutual Exclusivity Loss for Semi-Supervised Deep Learning](https://mlsanity.com/paper/1606.03141/) (2016)
- [f-VAEs: Improve VAEs with Conditional Flows](https://mlsanity.com/paper/1809.05861/) (2018)
- [Fine-grained Image-to-Image Transformation towards Visual Recognition](https://mlsanity.com/paper/2001.03856/) (2020)
- [Generative Model with Dynamic Linear Flow](https://mlsanity.com/paper/1905.03239/) (2019)
- [MSFD:Multi-Scale Receptive Field Face Detector](https://mlsanity.com/paper/1903.04147/) (2019)

## Abstract (arXiv)

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.