Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework

TL;DR

This paper introduces a Bayesian evidence framework for selecting and combining pre-trained CNNs in transfer learning, using a fast LS-SVM classifier that automatically estimates regularization parameters and improves performance across multiple datasets.

Contribution

The paper presents a novel Bayesian evidence approach for automatic CNN selection and ensemble construction in transfer learning, enhancing efficiency and accuracy.

Findings

Achieves state-of-the-art accuracy on 12 visual datasets.

Automatically estimates regularization parameters without grid search.

Effectively identifies optimal CNN ensembles using a greedy algorithm.

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.