Knowledge Distillation by On-the-Fly Native Ensemble

Part of Advances in Neural Information Processing Systems 31 (NeurIPS 2018)

Bibtex »Metadata »Paper »Reviews »


xu lan, Xiatian Zhu, Shaogang Gong


Knowledge distillation is effective to train the small and generalisable network models for meeting the low-memory and fast running requirements. Existing offline distillation methods rely on a strong pre-trained teacher, which enables favourable knowledge discovery and transfer but requires a complex two-phase training procedure. Online counterparts address this limitation at the price of lacking a high-capacity teacher. In this work, we present an On-the-fly Native Ensemble (ONE) learning strategy for one-stage online distillation. Specifically, ONE only trains a single multi-branch network while simultaneously establishing a strong teacher on-the-fly to enhance the learning of target network. Extensive evaluations show that ONE improves the generalisation performance of a variety of deep neural networks more significantly than alternative methods on four image classification dataset: CIFAR10, CIFAR100, SVHN, and ImageNet, whilst having the computational efficiency advantages.