Hint-dynamic Knowledge Distillation
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model. Existing efforts guide the distillation by matching their prediction logits, feature embedding, etc., while leaving how to efficiently utilize them in junction less explored. In this paper, we propose Hint-dynamic Knowledge Distillation, dubbed HKD, which excavates the knowledge from the teacher' s hints in a dynamic scheme. The guidance effect from the knowledge hints usually varies in different instances and learning stages, which motivates us to customize a specific hint-learning manner for each instance adaptively. Specifically, a meta-weight network is introduced to generate the instance-wise weight coefficients about knowledge hints in the perception of the dynamical learning progress of the student model. We further present a weight ensembling strategy to eliminate the potential bias of coefficient estimation by exploiting the historical statics. Experiments on standard benchmarks of CIFAR-100 and Tiny-ImageNet manifest that the proposed HKD well boost the effect of knowledge distillation tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge DistillationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation
One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hin…
ClusteringKnowledge DistillationModel CompressionKnowledge Condensation Distillation
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student. Existing methods focus on excavating the knowledge hints and transferring the whole knowledge to t…
Knowledge DistillationAdaptive Multi-Teacher Multi-level Knowledge Distillation
Knowledge distillation~(KD) is an effective learning paradigm for improving the performance of lightweight student networks by utilizing additional supervision knowledge distilled from teacher networks. Most pioneering s…
Knowledge DistillationInteractive Distillation for Cooperative Multi-Agent Reinforcement Learning
Knowledge distillation (KD) has the potential to accelerate MARL by employing a centralized teacher for decentralized students but faces key bottlenecks. Specifically, there are (1) challenges in synthesizing high-perfor…
Multi-agent Reinforcement LearningKnowledge DistillationOne-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation
Knowledge distillation~(KD) has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. However, most existing distillation methods are designed under the assum…
AllKnowledge Distillation