Heterogeneous Generative Knowledge Distillation with Masked Image Modeling
CoRR(2023)
摘要
Small CNN-based models usually require transferring knowledge from a large
model before they are deployed in computationally resource-limited edge
devices. Masked image modeling (MIM) methods achieve great success in various
visual tasks but remain largely unexplored in knowledge distillation for
heterogeneous deep models. The reason is mainly due to the significant
discrepancy between the Transformer-based large model and the CNN-based small
network. In this paper, we develop the first Heterogeneous Generative Knowledge
Distillation (H-GKD) based on MIM, which can efficiently transfer knowledge
from large Transformer models to small CNN-based models in a generative
self-supervised fashion. Our method builds a bridge between Transformer-based
models and CNNs by training a UNet-style student with sparse convolution, which
can effectively mimic the visual representation inferred by a teacher over
masked modeling. Our method is a simple yet effective learning paradigm to
learn the visual representation and distribution of data from heterogeneous
teacher models, which can be pre-trained using advanced generative methods.
Extensive experiments show that it adapts well to various models and sizes,
consistently achieving state-of-the-art performance in image classification,
object detection, and semantic segmentation tasks. For example, in the Imagenet
1K dataset, H-GKD improves the accuracy of Resnet50 (sparse) from 76.98
80.01
更多查看译文
关键词
heterogeneous generative knowledge distillation,masked image
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要