Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework
This work addresses the challenge of efficient and accurate model selection in transfer learning for visual recognition, though it is incremental as it builds on existing LS-SVM and Bayesian methods.
The authors tackled the problem of selecting pre-trained deep convolutional neural networks for transfer learning by proposing a Bayesian evidence framework that automatically estimates regularization parameters and selects the best CNN or ensemble, achieving state-of-the-art performance on 12 visual recognition datasets.
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.