Generalized Zero-Shot Learning Via Over-Complete Distribution
This work addresses the challenge of training deep neural networks to generalize to unseen classes, which is incremental as it builds on existing ZSL methods with specific enhancements.
The paper tackles the problem of zero-shot learning (ZSL) and generalized zero-shot learning (GZSL) by proposing a method to generate over-complete distributions using a Conditional Variational Autoencoder, combined with triplet and center losses for separability, resulting in improved performance on benchmark datasets SUN, CUB, and AWA2.
A well trained and generalized deep neural network (DNN) should be robust to both seen and unseen classes. However, the performance of most of the existing supervised DNN algorithms degrade for classes which are unseen in the training set. To learn a discriminative classifier which yields good performance in Zero-Shot Learning (ZSL) settings, we propose to generate an Over-Complete Distribution (OCD) using Conditional Variational Autoencoder (CVAE) of both seen and unseen classes. In order to enforce the separability between classes and reduce the class scatter, we propose the use of Online Batch Triplet Loss (OBTL) and Center Loss (CL) on the generated OCD. The effectiveness of the framework is evaluated using both Zero-Shot Learning and Generalized Zero-Shot Learning protocols on three publicly available benchmark databases, SUN, CUB and AWA2. The results show that generating over-complete distributions and enforcing the classifier to learn a transform function from overlapping to non-overlapping distributions can improve the performance on both seen and unseen classes.