Transfer Learning in CNNs Using Filter-Trees

Convolutional Neural Networks (CNNs) are very effective for many pattern recognition tasks. However, training deep CNNs needs extensive computation and large training data. In this paper we propose Bank of Filter-Trees (BFT) as a transfer learning mechanism for improving efficiency of learning CNNs. A filter-tree corresponding to a filter in k convolutional layer of a CNN is a subnetwork consisting of the filter along with all its connections to filters in all preceding layers. An ensemble of such filter-trees created from the k layers of many CNNs learnt on different but related tasks, forms the BFT. To learn a new CNN, we sample from the BFT to select a set of filter trees. This fixes the target net up to the k layer and only the remaining network would be learnt using training data of new task. Through simulations we demonstrate the effectiveness of this idea of BFT. This method constitutes a novel transfer learning technique where transfer is at a subnetwork level; transfer can be effected from multiple source networks; and, with no finetuning of the transferred weights, the performance achieved is on par with networks that are trained from scratch.