用AI自解释能力自动提升模型性能，无需人工干预。
IMPACTX: improving model performance by appropriately constraining the training with teacher explanations
- 将XAI输出作为自动化注意力机制融入训练过程
- 在三个数据集上均显著提升主流模型准确率
- 推理时直接生成可解释的特征图，无需额外工具
可解释人工智能（XAI）研究主要关注解释深度学习等AI模型的决策过程。近年来，越来越多工作探索如何利用XAI技术自动提升AI系统性能。本文提出IMPACTX，一种全新方法，通过XAI输出构建全自动注意力机制，无需外部知识或人工反馈。实验表明，与独立机器学习模型相比，IMPACTX在训练中融合基于XAI的注意力机制后性能得到提升。此外，该方法在推理阶段直接生成合理的特征重要性图，无需依赖外部XAI工具。评估使用三种主流深度学习模型（EfficientNet-B2、MobileNet、LeNet-5）及三个标准图像数据集（CIFAR-10、CIFAR-100、STL-10），结果表明IMPACTX在所有模型和数据集上均持续提升性能，并直接提供可解释性输出。
原文摘要 · Abstract (English)
The eXplainable Artificial Intelligence (XAI) research predominantly concentrates to provide explainations about AI model decisions, especially Deep Learning (DL) models. However, there is a growing interest in using XAI techniques to automatically improve the performance of the AI systems themselves. This paper proposes IMPACTX, a novel approach that leverages XAI as a fully automated attention mechanism, without requiring external knowledge or human feedback. Experimental results show that IMPACTX has improved performance respect to the standalone ML model by integrating an attention mechanism based an XAI method outputs during the model training. Furthermore, IMPACTX directly provides proper feature attribution maps for the model's decisions, without relying on external XAI methods during the inference process. Our proposal is evaluated using three widely recognized DL models (EfficientNet-B2, MobileNet, and LeNet-5) along with three standard image datasets: CIFAR-10, CIFAR-100, and STL-10. The results show that IMPACTX consistently improves the performance of all the inspected DL models across all evaluated datasets, and it directly provides appropriate explanations for its responses.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。