Multi-instance semantic similarity transferring for knowledge distillation

Haoran Zhao, Xin Sun*, Junyu Dong, Hui Yu, Gaige Wang

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    93 Downloads (Pure)

    Abstract

    Knowledge distillation is a popular paradigm for learning portable neural networks by transferring the knowledge from a large model into a smaller one. Most existing approaches enhance the student model by utilizing the similarity information between the categories of instance level provided by the teacher model. However, these works ignore the similarity correlation between different instances that plays an important role in confidence prediction. To tackle this issue, we propose a novel method in this paper, called multi-instance semantic similarity transferring for knowledge distillation (STKD), which aims to fully utilize the similarities between categories of multiple samples. Furthermore, we propose to better capture the similarity correlation between different instances by the mixup technique, which creates virtual samples by a weighted linear interpolation. Note that, our distillation loss can fully utilize the incorrect classes similarities by the mixed labels. The proposed approach promotes the performance of student model as the virtual sample created by multiple images produces a similar probability distribution in the teacher and student networks. Experiments and ablation studies on several public classification datasets including CIFAR-10, CIFAR-100, CINIC-10 and Tiny-ImageNet verify that this light-weight method can effectively boost the performance of the compact student model. It shows that STKD has substantially outperformed the vanilla knowledge distillation and achieved superior accuracy over the state-of-the-art knowledge distillation methods.

    Original languageEnglish
    Article number109832
    Number of pages10
    JournalKnowledge-Based Systems
    Volume256
    Early online date16 Sept 2022
    DOIs
    Publication statusPublished - 28 Nov 2022

    Keywords

    • Deep neural networks
    • Image classification
    • Knowledge distillation
    • Model compression

    Fingerprint

    Dive into the research topics of 'Multi-instance semantic similarity transferring for knowledge distillation'. Together they form a unique fingerprint.

    Cite this