提出OSCAR框架，量化并定位模型依赖的捷径特征。
Localising Shortcut Learning in Pixel Space via Ordinal Scoring Correlations for Attribution Representations (OSCAR)
- 通过排序相关性分析图像区域的归因图谱，实现像素级捷径定位。
- 在CelebA、CheXpert和ADNI数据集上验证了方法的稳定性和敏感性。
- 适用于医疗影像等人类不可见特征场景，适合模型审计与公平性优化。
深度神经网络常利用捷径学习，即训练数据中与标签相关但与任务语义无关的虚假线索。当这些线索关联敏感属性时，会导致模型偏差。现有方法多依赖定性、图像级检查，且假设线索为人可见，限制了其在医学影像等领域的应用。本文提出OSCAR（基于归因表示的序数评分相关性），一种模型无关的定量框架，用于量化捷径学习并定位捷径特征。OSCAR将图像级任务归因图转换为数据集级的区域排名谱，并在三个模型间比较：平衡基线模型（BA）、测试模型（TS）和敏感属性预测器（SA）。通过计算成对、部分及偏差相关的相关性，生成一组度量指标，刻画TS对捷径的依赖程度，并给出贡献最大的图像区域排名。在CelebA、CheXpert和ADNI上的实验表明，该相关性具备（i）跨种子和划分的稳定性，（ii）对训练数据中捷径特征与标签关联程度的敏感性，（iii）区分局部与弥散型捷径的能力。作为应用示例，我们展示基于识别出的捷径区域进行测试时衰减，可有效缓解最差组性能差距。OSCAR提供轻量级像素空间审计，输出统计决策规则与空间图，支持模型的测试、定位与缓解。代码已开源：https://github.com/acharaakshit/oscar
原文摘要 · Abstract (English)
Deep neural networks often exploit shortcuts. These are spurious cues which are associated with output labels in the training data but are unrelated to task semantics. When the shortcut features are associated with sensitive attributes, shortcut learning can lead to biased model performance. Existing methods for localising and understanding shortcut learning are mostly based upon qualitative, image-level inspection and assume cues are human-visible, limiting their use in domains such as medical imaging. We introduce OSCAR (Ordinal Scoring Correlations for Attribution Representations), a model-agnostic framework for quantifying shortcut learning and localising shortcut features. OSCAR converts image-level task attribution maps into dataset-level rank profiles of image regions and compares them across three models: a balanced baseline model (BA), a test model (TS), and a sensitive attribute predictor (SA). By computing pairwise, partial, and deviation-based correlations on these rank profiles, we produce a set of quantitative metrics that characterise the degree of shortcut reliance for TS, together with a ranking of image-level regions that contribute most to it. Experiments on CelebA, CheXpert, and ADNI show that our correlations are (i) stable across seeds and partitions, (ii) sensitive to the level of association between shortcut features and output labels in the training data, and (iii) able to distinguish localised from diffuse shortcut features. As an illustration of the utility of our method, we show how worst-group performance disparities can be reduced using a simple test-time attenuation approach based on the identified shortcut regions. OSCAR provides a lightweight, pixel-space audit that yields statistical decision rules and spatial maps, enabling users to test, localise, and mitigate shortcut reliance. The code is available at https://github.com/acharaakshit/oscar
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。