Discriminative Transfer Learning with Tree-based Priors

Abstract

High capacity classifiers, such as deep neural networks, often struggle on classes that have very few training examples. We propose a method for improving clas-sification performance for such classes by discovering similar classes and trans-ferring knowledge among them. Our method learns to organize the classes into a tree hierarchy. This tree structure imposes a prior over the classifier’s param-eters. We show that the performance of deep neural networks can be improved by applying these priors to the weights in the last layer. Our method combines the strength of discriminatively trained deep neural networks, which typically re-quire large amounts of training data, with tree-based priors, making deep neural networks work well on infrequent classes as well. We also propose an algorithm for learning the underlying tree structure. Starting from an initial pre-specified tree, this algorithm modifies the tree to make it more pertinent to the task being solved, for example, removing semantic relationships in favour of visual ones for an image classification task. Our method achieves state-of-the-art classification results on the CIFAR-100 image data set and the MIR Flickr image-text data set. 1