A Scalable Approach for Facial Action Unit Classifier Training UsingNoisy Data for Pre-Training
This addresses the labor-intensive task of facial action coding for researchers and practitioners in computer vision, offering a scalable and open-source method, though it is incremental as it builds on existing pre-training techniques.
The paper tackles the problem of facial action unit recognition by showing that pre-training a simple CNN on a large, noisy dataset improves performance over more complex state-of-the-art DNNs, achieving an average F1-score of 0.60 compared to 0.57 on the DISFA dataset.
Machine learning systems are being used to automate many types of laborious labeling tasks. Facial actioncoding is an example of such a labeling task that requires copious amounts of time and a beyond average level of human domain expertise. In recent years, the use of end-to-end deep neural networks has led to significant improvements in action unit recognition performance and many network architectures have been proposed. Do the more complex deep neural network(DNN) architectures perform sufficiently well to justify the additional complexity? We show that pre-training on a large diverse set of noisy data can result in even a simple CNN model improving over the current state-of-the-art DNN architectures.The average F1-score achieved with our proposed method on the DISFA dataset is 0.60, compared to a previous state-of-the-art of 0.57. Additionally, we show how the number of subjects and number of images used for pre-training impacts the model performance. The approach that we have outlined is open-source, highly scalable, and not dependent on the model architecture. We release the code and data: https://github.com/facialactionpretrain/facs.