Zero-shot Learning with Class Description Regularization
This work addresses the challenge of improving zero-shot learning accuracy for tasks like recognition and classification, which is incremental but practically useful for applications with limited labeled data.
The paper tackles the problem of generative zero-shot learning by introducing a novel regularization method that encourages models to focus more on class descriptions, achieving improved performance over multiple state-of-the-art models on datasets like CUB, NABirds, AWA2, aPY, and SUN.
The purpose of generative Zero-shot learning (ZSL) is to learning from seen classes, transfer the learned knowledge, and create samples of unseen classes from the description of these unseen categories. To achieve better ZSL accuracies, models need to better understand the descriptions of unseen classes. We introduce a novel form of regularization that encourages generative ZSL models to pay more attention to the description of each category. Our empirical results demonstrate improvements over the performance of multiple state-of-the-art models on the task of generalized zero-shot recognition and classification when trained on textual description-based datasets like CUB and NABirds and attribute-based datasets like AWA2, aPY and SUN.