Context-based image explanations for deep neural networks
Context-based image explanations for deep neural networks
复制标题
DOI：
10.1016/j.imavis.2021.104310
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
S. Anjomshoae;Daniel Omeiza;Lili Jiang
中科院分区：
文献类型：
--
作者：
S. Anjomshoae;Daniel Omeiza;Lili Jiang
随着机器学习在决策场景中的使用越来越多，人们对解释和理解机器学习模型的结果越来越感兴趣。尽管这种日益增长的兴趣，现有的作品的可解释性和解释主要是针对专家用户。在许多可用的和实际的应用中忽略了对一般用户的解释（例如，图像标记、字幕生成）。对于非技术用户来说，了解特性以及它们如何影响特定于实例的预测以满足合理性的需要是很重要的。在本文中，我们提出了一个模型无关的方法生成基于上下文的解释，针对一般用户。我们实现部分掩蔽分段组件，以确定场景分类任务中每个片段的上下文重要性。然后，我们根据特征重要性生成解释。我们提出了视觉和基于文本的解释：（i）显着性图提出了相关的组件与描述性的文本理由，（ii）视觉地图与彩色条形图显示每个功能的相对重要性的预测。使用用户研究（N= 50）评估解释，我们观察到我们提出的解释方法在视觉上优于现有的基于梯度和遮挡的方法。因此，我们所提出的解释方法可以部署到解释模型的决定，以非专家用户在现实世界中的应用。
With the increased use of machine learning in decision-making scenarios, there has been a growing interest in explaining and understanding the outcomes of machine learning models. Despite this growing interest, existing works on interpretability and explanations have been mostly intended for expert users. Explanations for general users have been neglected in many usable and practical applications (e.g., image tagging, caption generation). It is important for non-technical users to understand features and how they affect an instance-specific prediction to satisfy the need for justification. In this paper, we propose a model-agnostic method for generating context-based explanations aiming for general users. We implement partial masking on segmented components to identify the contextual importance of each segment in scene classification tasks. We then generate explanations based on feature importance. We present visual and text-based explanations: (i) saliency map presents the pertinent components with a descriptive textual justification, (ii) visual map with a color bar graph showing the relative importance of each feature for a prediction. Evaluating the explanations using a user study (N= 50), we observed that our proposed explanation method visually outperformed existing gradient and occlusion based methods. Hence, our proposed explanation method could be deployed to explain models’ decisions to non-expert users in real-world applications.