Adversarial Co distillation Learning for Image Recognition
Pattern Recognition, pp. 1076592020.
Knowledge distillation is an effective way to transfer the knowledge from a pre-trained teacher model to a student model. Co-distillation, as an online variant of distillation, further accelerates the training process and paves a new way to explore the “dark knowledge” by training n models in parallel. In this paper, we explore the “diver...More
Full Text (Upload PDF)
PPT (Upload PPT)