Class2Str: End to End Latent Hierarchy Learning

TL;DR

This paper introduces Class2Str, an end-to-end method that learns a latent hierarchy of classes in neural networks, improving interpretability and efficiency while maintaining high accuracy on CIFAR and ImageNet datasets.

Contribution

It proposes the Latent Hierarchy Classifier and Class2Str mapping, enabling arbitrary-level hierarchy learning and improved accuracy over previous hierarchical models.

Findings

Recovers accuracy with fewer parameters.

Learns hierarchies at multiple levels.

Groups visually similar classes together.

Abstract

Deep neural networks for image classification typically consists of a convolutional feature extractor followed by a fully connected classifier network. The predicted and the ground truth labels are represented as one hot vectors. Such a representation assumes that all classes are equally dissimilar. However, classes have visual similarities and often form a hierarchy. Learning this latent hierarchy explicitly in the architecture could provide invaluable insights. We propose an alternate architecture to the classifier network called the Latent Hierarchy (LH) Classifier and an end to end learned Class2Str mapping which discovers a latent hierarchy of the classes. We show that for some of the best performing architectures on CIFAR and Imagenet datasets, the proposed replacement and training by LH classifier recovers the accuracy, with a fraction of the number of parameters in the classifier part. Compared to the previous work of HDCNN, which also learns a 2 level hierarchy, we are able to learn a hierarchy at an arbitrary number of levels as well as obtain an accuracy improvement on the Imagenet classification task over them. We also verify that many visually similar classes are grouped together, under the learnt hierarchy.