Introspective Learning by Distilling Knowledge from Online Self-explanation
This work addresses the challenge of enhancing model performance in machine learning by using internal explanations, which is incremental as it builds on existing knowledge distillation and explanation methods.
The paper tackles the problem of improving deep neural network learning by leveraging self-explanations as privileged information, inspired by knowledge distillation, and results in models that outperform standard training and other regularization methods while being competitive with teacher-based approaches without requiring external networks.
In recent years, many explanation methods have been proposed to explain individual classifications of deep neural networks. However, how to leverage the created explanations to improve the learning process has been less explored. As the privileged information, the explanations of a model can be used to guide the learning process of the model itself. In the community, another intensively investigated privileged information used to guide the training of a model is the knowledge from a powerful teacher model. The goal of this work is to leverage the self-explanation to improve the learning process by borrowing ideas from knowledge distillation. We start by investigating the effective components of the knowledge transferred from the teacher network to the student network. Our investigation reveals that both the responses in non-ground-truth classes and class-similarity information in teacher's outputs contribute to the success of the knowledge distillation. Motivated by the conclusion, we propose an implementation of introspective learning by distilling knowledge from online self-explanations. The models trained with the introspective learning procedure outperform the ones trained with the standard learning procedure, as well as the ones trained with different regularization methods. When compared to the models learned from peer networks or teacher networks, our models also show competitive performance and requires neither peers nor teachers.