Exploiting Convolution Filter Patterns for Transfer Learning

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)(2017)

引用 17|浏览39
暂无评分
摘要
In this paper, we introduce a new regularization technique for transfer learning. The aim of the proposed approach is to capture statistical relationships among convolution filters learned from a well-trained network and transfer this knowledge to another network. Since convolution filters of the prevalent deep Convolutional Neural Network (CNN) models share a number of similar patterns, in order to speed up the learning procedure, we capture such correlations by Gaussian Mixture Models (GMMs) and transfer them using a regularization term. We have conducted extensive experiments on the CIFAR10, Places2, and CMPlaces datasets to assess generalizability, task transferability, and cross-model transferability of the proposed approach, respectively. The experimental results show that the feature representations have efficiently been learned and transferred through the proposed statistical regularization scheme. Moreover, our method is an architecture independent approach, which is applicable for a variety of CNN architectures.
更多
查看译文
关键词
learning procedure,regularization term,task transferability,cross-model transferability,statistical regularization scheme,convolution filter patterns,transfer learning,regularization technique,statistical relationships,Gaussian mixture models,deep convolutional neural network models,CIFAR10 dataset,Places2 dataset,CM-Places dataset
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