Modern Artificial Intelligence (AI) systems, especially Deep Learning (DL) models, poses challenges in understanding their inner workings by AI researchers. eXplainable Artificial Intelligence (XAI) inspects internal mechanisms of AI models providing explanations about their decisions. While current XAI research predominantly concentrates on explaining AI systems, there is a growing interest in using XAI techniques to automatically improve the performance of AI systems themselves. This paper proposes a general framework for automatically improving the performance of pre-trained DL classifiers using XAI methods, avoiding the computational overhead associated with retraining complex models from scratch. In particular, we outline the possibility of two different learning strategies for implementing this architecture, which we will call auto-encoder-based and encoder-decoder-based, and discuss their key aspects.

翻译：现代人工智能系统，特别是深度学习模型，其内部运作机制对AI研究者而言仍存在理解挑战。可解释人工智能通过检查AI模型的内部机理，为其决策提供解释。当前XAI研究主要聚焦于解释AI系统，但利用XAI技术自动提升AI系统性能的研究正日益受到关注。本文提出一种通用框架，通过XAI方法自动改善预训练深度学习分类器的性能，避免因从头训练复杂模型而产生的计算开销。具体而言，我们阐述了实现该架构的两种学习策略（即基于自编码器和基于编码器-解码器的策略）的可行性，并讨论了其关键特性。