Knowledge Distillation via Instance-level Sequence Learning
This work addresses the challenge of improving knowledge distillation efficiency for training compact neural networks, representing an incremental advancement over existing methods.
The paper tackles the problem of knowledge distillation by proposing a curriculum learning framework that guides the student network gradually using ordered samples, achieving the best performance with fewer iterations on CIFAR-10, CIFAR-100, SVHN, and CINIC-10 datasets compared to state-of-the-art methods.
Recently, distillation approaches are suggested to extract general knowledge from a teacher network to guide a student network. Most of the existing methods transfer knowledge from the teacher network to the student via feeding the sequence of random mini-batches sampled uniformly from the data. Instead, we argue that the compact student network should be guided gradually using samples ordered in a meaningful sequence. Thus, it can bridge the gap of feature representation between the teacher and student network step by step. In this work, we provide a curriculum learning knowledge distillation framework via instance-level sequence learning. It employs the student network of the early epoch as a snapshot to create a curriculum for the student network's next training phase. We carry out extensive experiments on CIFAR-10, CIFAR-100, SVHN and CINIC-10 datasets. Compared with several state-of-the-art methods, our framework achieves the best performance with fewer iterations.