Exploiting Convolution Filter Patterns for Transfer Learning
This addresses the challenge of slow learning in transfer learning for computer vision, though it is incremental as it builds on existing regularization and statistical modeling techniques.
The paper tackles the problem of speeding up transfer learning in CNNs by capturing statistical patterns in convolution filters using Gaussian Mixture Models and transferring them via regularization, resulting in efficient feature learning and transfer across datasets like CIFAR10, Places2, and CMPlaces.
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.