PrUE: Distilling Knowledge from Sparse Teacher Networks
This work addresses model compression for deployment in resource-constrained environments, offering an incremental improvement over existing knowledge distillation techniques.
The paper tackles the problem of knowledge distillation failing when there is a large size gap between teacher and student networks by introducing PrUE, a pruning method that reduces teacher certainty to produce softer labels, resulting in improved student performance on datasets like CIFAR-10/100 and ImageNet.
Although deep neural networks have enjoyed remarkable success across a wide variety of tasks, their ever-increasing size also imposes significant overhead on deployment. To compress these models, knowledge distillation was proposed to transfer knowledge from a cumbersome (teacher) network into a lightweight (student) network. However, guidance from a teacher does not always improve the generalization of students, especially when the size gap between student and teacher is large. Previous works argued that it was due to the high certainty of the teacher, resulting in harder labels that were difficult to fit. To soften these labels, we present a pruning method termed Prediction Uncertainty Enlargement (PrUE) to simplify the teacher. Specifically, our method aims to decrease the teacher's certainty about data, thereby generating soft predictions for students. We empirically investigate the effectiveness of the proposed method with experiments on CIFAR-10/100, Tiny-ImageNet, and ImageNet. Results indicate that student networks trained with sparse teachers achieve better performance. Besides, our method allows researchers to distill knowledge from deeper networks to improve students further. Our code is made public at: \url{https://github.com/wangshaopu/prue}.