From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process
This work addresses a key challenge in zero-shot learning for computer vision by enhancing model generalization across both seen and unseen classes, though it is incremental as it builds on existing methods.
The paper tackles the performance gap between seen and unseen classes in generalized zero-shot learning by proposing a simple adaptation process that penalizes seen classes and optimizes hyper-parameters, resulting in average GZSL performance improvements from 28.5 to 42.2 on CUB and from 28.2 to 57.1 on AwA2.
Zero-shot learning (ZSL) is concerned with the recognition of previously unseen classes. It relies on additional semantic knowledge for which a mapping can be learned with training examples of seen classes. While classical ZSL considers the recognition performance on unseen classes only, generalized zero-shot learning (GZSL) aims at maximizing performance on both seen and unseen classes. In this paper, we propose a new process for training and evaluation in the GZSL setting; this process addresses the gap in performance between samples from unseen and seen classes by penalizing the latter, and enables to select hyper-parameters well-suited to the GZSL task. It can be applied to any existing ZSL approach and leads to a significant performance boost: the experimental evaluation shows that GZSL performance, averaged over eight state-of-the-art methods, is improved from 28.5 to 42.2 on CUB and from 28.2 to 57.1 on AwA2.