Self-knowledge distillation for surgical phase recognition

Jinglu Zhang, Santiago Barbarisi, Abdolrahim Kadkhodamohammadi, Danail Stoyanov, Imanol Luengo

Abstract: Advances in surgical phase recognition are generally led by training deeper networks. Rather than going further with a more complex solution, we believe that current models can be exploited better. We propose a self-knowledge distillation framework that can be integrated into current state-of-the-art (SOTA) models without requiring any extra complexity to the models or annotations.