Data slice-finding is an emerging technique for evaluating machine learning models. It works by identifying subgroups within a specified dataset that exhibit poor performance, often defined by distinct feature sets or meta-information. However, in the context of unstructured image data, data slice-finding poses two notable challenges: it requires additional metadata -- a laborious and costly requirement, and also demands non-trivial efforts for interpreting the root causes of the underperformance within data slices. To address these challenges, we introduce AttributionScanner, an innovative human-in-the-loop Visual Analytics (VA) system, designed for data-slicing-based machine learning (ML) model validation. Our approach excels in identifying interpretable data slices, employing explainable features extracted through the lens of Explainable AI (XAI) techniques, and removing the necessity for additional metadata of textual annotations or cross-model embeddings. AttributionScanner demonstrates proficiency in pinpointing critical model issues, including spurious correlations and mislabeled data. Our novel VA interface visually summarizes data slices, enabling users to gather insights into model behavior patterns effortlessly. Furthermore, our framework closes the ML Development Cycle by empowering domain experts to address model issues by using a cutting-edge neural network regularization technique. The efficacy of AttributionScanner is underscored through two prototype use cases, elucidating its substantial effectiveness in model validation for vision-centric tasks. Our approach paves the way for ML researchers and practitioners to drive interpretable model validation in a data-efficient way, ultimately leading to more reliable and accurate models.

翻译：数据切片发现是一种新兴的机器学习模型评估技术。该方法通过识别指定数据集中性能表现不佳的子群（通常由特定特征集或元信息定义）来工作。然而在非结构化图像数据场景下，数据切片发现面临两大挑战：需要额外元数据（需耗费大量人力与成本），且需投入大量精力解释数据切片中性能欠佳的根本原因。为应对这些挑战，我们提出AttributionScanner——一种创新的基于人机协同的可视分析（VA）系统，专为基于数据切片的机器学习（ML）模型验证而设计。我们的方法通过提取可解释人工智能（XAI）技术视角下的可解释特征，在无需文本标注或跨模型嵌入等额外元数据的情况下，擅长识别可解释的数据切片。AttributionScanner在定位关键模型问题（包括虚假相关性和数据标注错误）方面表现出色。创新性的VA界面通过可视化摘要呈现数据切片，使用户能够轻松洞察模型行为模式。此外，本框架通过采用前沿的神经网络正则化技术赋能领域专家解决模型问题，从而闭环机器学习开发周期。通过两个原型用例验证，AttributionScanner在视觉密集型任务的模型验证中展现了显著效能。本方法为机器学习研究者和实践者开辟了数据高效的模型可解释验证路径，最终推动更可靠和精确的模型构建。