Recent research on Generalized Zero-Shot Learning (GZSL) has focused primarily on generation-based methods. However, current literature has overlooked the fundamental principles of these methods and has made limited progress in a complex manner. In this paper, we aim to deconstruct the generator-classifier framework and provide guidance for its improvement and extension. We begin by breaking down the generator-learned unseen class distribution into class-level and instance-level distributions. Through our analysis of the role of these two types of distributions in solving the GZSL problem, we generalize the focus of the generation-based approach, emphasizing the importance of (i) attribute generalization in generator learning and (ii) independent classifier learning with partially biased data. We present a simple method based on this analysis that outperforms SotAs on four public GZSL datasets, demonstrating the validity of our deconstruction. Furthermore, our proposed method remains effective even without a generative model, representing a step towards simplifying the generator-classifier structure. Our code is available at \url{https://github.com/cdb342/DGZ}.

翻译：近期关于广义零样本学习（GZSL）的研究主要聚焦于生成式方法。然而，现有文献忽视了这些方法的基本原理，且进展有限且方式复杂。本文旨在解构生成器-分类器框架，为其改进与扩展提供指导。我们首先将生成器学习到的未见类分布分解为类级分布与实例级分布。通过分析这两类分布在解决GZSL问题中的作用，我们归纳了生成式方法的核心关注点，强调了以下两个关键要素：(i) 生成器学习中的属性泛化能力，(ii) 基于部分偏置数据的独立分类器学习。基于该分析，我们提出了一种简单方法，在四个公开GZSL数据集上超越了当前最优方法（SotAs），验证了解构的有效性。此外，即使在没有生成模型的情况下，我们提出的方法仍然有效，这标志着向简化生成器-分类器结构迈出了一步。我们的代码开源在 \url{https://github.com/cdb342/DGZ}。