This paper is aimed at creating extremely small and fast convolutional neural networks (CNN) for the problem of facial expression recognition (FER) from frontal face images. To this end, we employed the popular knowledge distillation (KD) method and identified two major shortcomings with its use: 1) a fine-grained grid search is needed for tuning the temperature hyperparameter and 2) to find the optimal size-accuracy balance, one needs to search for the final network size (i.e. the compression rate). On the other hand, KD is proved to be useful for model compression for the FER problem, and we discovered that its effects gets more and more significant with the decreasing model size. In addition, during the search for a network architecture, we hypothesized that translation invariance achieved using max-pooling layers would not be useful for the FER problem as the expressions are sensitive to small, pixel-wise changes around the eye and the mouth. However, we have found an intriguing improvement on generalization when max-pooling is used. Experiments are made on two widelyused FER datasets, CK+ and Oulu-CASIA. Our smallest model (MicroExpNet), obtained using knowledge distillation, is less than 1MB in size and works at 1851 frames per second on an Intel i7 CPU. Despite being less accurate than the state-of-the-art, MicroExpNet still provides significant insights on the creation of a micro architecture for the FER problem.
Deploying convolutional neural networks to mobile or embedded devices is often prohibited by limited memory and computational resources. This is particularly problematic for the most successful networks, which tend to be very large and require long inference times. Many alternative approaches have been developed for compressing neural networks based on pruning, regularization, quantization or distillation. In this paper, we propose the “Knowledge Distillation with Dynamic Pruning” (KDDP), which trains a dynamically pruned compact student network under the guidance of a large teacher network. In KDDP, we train the student network with supervision from the teacher network, while applying L1 regularization on the neuron activations in a fully-connected layer. Subsequently, we prune inactive neurons. Our method automatically determines the final size of the student model. We evaluate the compression rate and accuracy of the resulting networks on an image classification dataset, and compare them to results obtained by Knowledge Distillation (KD). Compared to KD, our method produces better accuracy and more compact models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.