Multi-granularity for knowledge distillation
Considering the fact that students have different abilities to understand the knowledge imparted by teachers, a multi-granularity distillation mechanism is proposed for transferring more understandable knowledge for student networks. A multi-granularity self-analyzing module of the teacher network is designed, which enables the student network to learn knowledge from different teaching patterns. Furthermore, a stable excitation scheme is proposed for robust supervision for the student training. The proposed distillation mechanism can be embedded into different distillation frameworks, which are taken as baselines. Experiments show the mechanism improves the accuracy by 0.58% on average and by 1.08% in the best over the baselines, which makes its performance superior to the state-of-the-arts. It is also exploited that the student's ability of fine-tuning and robustness to noisy inputs can be improved via the proposed mechanism. The code is available at https://github.com/shaoeric/multi-granularity-distillation.
Code (1)
Tasks
Knowledge DistillationPerson Re-IdentificationSimilar Papers 제목 키워드 기반
Multi-Granularity Structural Knowledge Distillation for Language Model Compression
Transferring the knowledge to a small model through distillation has raised great interest in recent years. Prevailing methods transfer the knowledge derived from mono-granularity language units (e.g., token-level or sam…
Knowledge DistillationLanguage ModelingLanguage ModellingModel Compression+1Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation
This paper explores the Class-Incremental Source-Free Unsupervised Domain Adaptation (CI-SFUDA) problem, where the unlabeled target data come incrementally without access to labeled source instances. This problem poses t…
class-incremental learningDomain AdaptationRepresentation LearningSource-Free Domain Adaptation+1Multi-Granularity Contrastive Knowledge Distillation for Multimodal Named Entity Recognition
It is very valuable to recognize named entities from short and informal multimodal posts in this age of information explosion. Despite existing methods success in multi-modal named entity recognition (MNER), they rely on…
Knowledge DistillationMulti-modal Named Entity Recognitionnamed-entity-recognitionNamed Entity Recognition+1Adaptive Knowledge Distillation between Text and Speech Pre-trained Models
Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models th…
Knowledge DistillationSpoken Language UnderstandingMuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification
Recent works have introduced GNN-to-MLP knowledge distillation (KD) frameworks to combine both GNN's superior performance and MLP's fast inference speed. However, existing KD frameworks are primarily designed for node cl…
ClassificationGraph ClassificationKnowledge DistillationNode Classification