Despite the fast progress of explanation techniques in modern Deep Neural Networks (DNNs) where the main focus is handling "how to generate the explanations", advanced research questions that examine the quality of the explanation itself (e.g., "whether the explanations are accurate") and improve the explanation quality (e.g., "how to adjust the model to generate more accurate explanations when explanations are inaccurate") are still relatively under-explored. To guide the model toward better explanations, techniques in explanation supervision - which add supervision signals on the model explanation - have started to show promising effects on improving both the generalizability as and intrinsic interpretability of Deep Neural Networks. However, the research on supervising explanations, especially in vision-based applications represented through saliency maps, is in its early stage due to several inherent challenges: 1) inaccuracy of the human explanation annotation boundary, 2) incompleteness of the human explanation annotation region, and 3) inconsistency of the data distribution between human annotation and model explanation maps. To address the challenges, we propose a generic RES framework for guiding visual explanation by developing a novel objective that handles inaccurate boundary, incomplete region, and inconsistent distribution of human annotations, with a theoretical justification on model generalizability. Extensive experiments on two real-world image datasets demonstrate the effectiveness of the proposed framework on enhancing both the reasonability of the explanation and the performance of the backbone DNNs model.
翻译:尽管现代深神经网络(DNNs)的解释技术进展迅速,其主要重点是处理“如何产生解释”的“如何产生解释”、审查解释本身质量(例如“解释是否准确”)、提高解释质量(例如“在解释不准确时如何调整模型以产生更准确的解释”)的先进研究问题,尽管在现代深神经网络(DNNs)的解释技术方面进展迅速,但是,为了引导模型更好地解释,解释监督技术(在模型解释中增加监督信号)已开始显示对改进深神经网络的一般性和内在解释的有希望效果;然而,由于若干固有的挑战,监督解释本身的质量(例如“解释是否准确”)、改进解释质量(例如“在解释不准确时如何调整模型以产生更准确的解释”)、改进解释质量(例如“在解释解释不准确的情况下如何调整模型”模型模型)的研究尚处于早期阶段;为了指导视觉解释,我们提出了一个通用的RES框架,即制定新的目标,处理不准确的边界、不完全的理论性,同时说明关于加强全球总体解释结构结构结构框架,同时说明关于提高全球范围的真正解释。