Nowadays, deep vision models are being widely deployed in safety-critical applications, e.g., autonomous driving, and explainability of such models is becoming a pressing concern. Among explanation methods, counterfactual explanations aim to find minimal and interpretable changes to the input image that would also change the output of the model to be explained. Such explanations point end-users at the main factors that impact the decision of the model. However, previous methods struggle to explain decision models trained on images with many objects, e.g., urban scenes, which are more difficult to work with but also arguably more critical to explain. In this work, we propose to tackle this issue with an object-centric framework for counterfactual explanation generation. Our method, inspired by recent generative modeling works, encodes the query image into a latent space that is structured in a way to ease object-level manipulations. Doing so, it provides the end-user with control over which search directions (e.g., spatial displacement of objects, style modification, etc.) are to be explored during the counterfactual generation. We conduct a set of experiments on counterfactual explanation benchmarks for driving scenes, and we show that our method can be adapted beyond classification, e.g., to explain semantic segmentation models. To complete our analysis, we design and run a user study that measures the usefulness of counterfactual explanations in understanding a decision model. Code is available at https://github.com/valeoai/OCTET.

翻译：如今，深度视觉模型正广泛应用于安全关键场景（如自动驾驶），这类模型的可解释性已成为紧迫问题。在众多解释方法中，反事实解释旨在寻找对输入图像的最小且可解释的修改，从而改变待解释模型的输出。此类解释可帮助最终用户了解影响模型决策的主要因素。然而，先前方法难以解释针对包含多物体图像（如城市街景）训练的决策模型——这类场景处理难度更高，但显然也需要更关键的解释。本文提出了一种以对象为中心的框架来解决这一问题，用于生成反事实解释。受近期生成式建模工作的启发，我们的方法将查询图像编码至一个结构化的潜在空间，以便于进行对象级操作。通过此方式，该方法使最终用户能够控制在反事实生成过程中探索哪些搜索方向（例如，对象的空间位移、风格修改等）。我们在驾驶场景的反事实解释基准上开展了一系列实验，并展示了该方法可被扩展至分类任务之外，例如用以解释语义分割模型。为完善分析，我们设计并实施了一项用户研究，衡量反事实解释在理解决策模型方面的实用性。代码已开源：https://github.com/valeoai/OCTET。