Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks
This work addresses the need for faster neural networks in real-time applications, but it is incremental as it builds on existing knowledge distillation methods.
The paper tackles the problem of accelerating neural networks for real-time applications by using knowledge distillation with conditional adversarial networks to train small student networks, achieving improved efficiency with specific trade-offs in inference time and accuracy.
There is an increasing interest on accelerating neural networks for real-time applications. We study the student-teacher strategy, in which a small and fast student network is trained with the auxiliary information learned from a large and accurate teacher network. We propose to use conditional adversarial networks to learn the loss function to transfer knowledge from teacher to student. The proposed method is particularly effective for relatively small student networks. Moreover, experimental results show the effect of network size when the modern networks are used as student. We empirically study the trade-off between inference time and classification accuracy, and provide suggestions on choosing a proper student network.