A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders

TL;DR

This paper introduces a novel zero shot learning approach using conditional variational autoencoders to generate samples from class attributes, enabling improved classification of unseen classes in image recognition tasks.

Contribution

It proposes a generative model based on conditional variational autoencoders for zero shot learning, outperforming existing methods on benchmark datasets.

Findings

Outperforms state-of-the-art methods on four benchmark datasets.

Effective in generalized zero shot learning where training and test classes overlap.

Generates realistic samples from class attributes for improved classification.

Abstract

Zero shot learning in Image Classification refers to the setting where images from some novel classes are absent in the training data but other information such as natural language descriptions or attribute vectors of the classes are available. This setting is important in the real world since one may not be able to obtain images of all the possible classes at training. While previous approaches have tried to model the relationship between the class attribute space and the image space via some kind of a transfer function in order to model the image space correspondingly to an unseen class, we take a different approach and try to generate the samples from the given attributes, using a conditional variational autoencoder, and use the generated samples for classification of the unseen classes. By extensive testing on four benchmark datasets, we show that our model outperforms the state of the art, particularly in the more realistic generalized setting, where the training classes can also appear at the test time along with the novel classes.