Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework
Abstract
We propose a Bayesian evidence framework to facilitate transfer learning from pre-trained deep convolutional neural networks (CNNs). Our framework is formulated on top of a least squares SVM (LS-SVM) classifier, which is simple and fast in both training and testing, and achieves competitive performance in practice. The regularization parameters in LS-SVM is estimated automatically without grid search and cross-validation by maximizing evidence, which is a useful measure to select the best performing CNN out of multiple candidates for transfer learning; the evidence is optimized efficiently by employing Aitken's delta-squared process, which accelerates convergence of fixed point update. The proposed Bayesian evidence framework also provides a good solution to identify the best ensemble of heterogeneous CNNs through a greedy algorithm. Our Bayesian evidence framework for transfer learning is tested on 12 visual recognition datasets and illustrates the state-of-the-art performance consistently in terms of prediction accuracy and modeling efficiency.
Cite
@article{arxiv.1506.02565,
title = {Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework},
author = {Yong-Deok Kim and Taewoong Jang and Bohyung Han and Seungjin Choi},
journal= {arXiv preprint arXiv:1506.02565},
year = {2016}
}
Comments
Appearing in CVPR-2016 (oral presentation)