通过合成数据量化背景对交通标志识别中分类与特征重要性的影响。
Measuring the Effect of Background on Classification and Feature Importance in Deep Learning for AV Perception
- 构建六组合成数据，仅改变相机变化和背景相关性来隔离影响因素。
- 发现背景特征重要性随训练域变化而显著上升，最高达78%。
- 为解释模型决策提供可量化的依据，适合关注模型可解释性的研究者。
现有可解释人工智能方法通常分析输入特征对分类任务的重要性，如使用SHAP、GradCAM等方法评估图像空间区域对分类结果的影响。结合真实标注的物体位置信息（如二值掩码），可判断分类是否聚焦于物体像素或背景像素——前者被视为健康分类，后者暗示对虚假相关性的过拟合。然而，这些直观解释难以量化验证，导致解释本身缺乏可信度。主要原因在于真实数据中相关性难以避免，其是否为虚假存在争议；而合成数据虽可主动控制相关性，但常缺乏足够的真实感与随机性量化。为此，我们系统生成六组用于交通标志识别的合成数据集，仅在相机变化程度和背景相关性上不同，以量化背景相关性、不同等级相机变化及标志形状对分类性能与背景特征重要性的影响。结果揭示了在训练域变化时，背景特征重要性如何随时间增长，最大可达78%，并提供了背景依赖性与模型性能之间关系的定量分析。数据集下载地址：synset.de/datasets/synset-signset-ger/background-effect
原文摘要 · Abstract (English)
Common approaches to explainable AI (XAI) for deep learning focus on analyzing the importance of input features on the classification task in a given model: saliency methods like SHAP and GradCAM are used to measure the impact of spatial regions of the input image on the classification result. Combined with ground truth information about the location of the object in the input image (e.g., a binary mask), it is determined whether object pixels had a high impact on the classification result, or whether the classification focused on background pixels. The former is considered to be a sign of a healthy classifier, whereas the latter is assumed to suggest overfitting on spurious correlations. A major challenge, however, is that these intuitive interpretations are difficult to test quantitatively, and hence the output of such explanations lacks an explanation itself. One particular reason is that correlations in real-world data are difficult to avoid, and whether they are spurious or legitimate is debatable. Synthetic data in turn can facilitate to actively enable or disable correlations where desired but often lack a sufficient quantification of realism and stochastic properties. [...] Therefore, we systematically generate six synthetic datasets for the task of traffic sign recognition, which differ only in their degree of camera variation and background correlation [...] to quantify the isolated influence of background correlation, different levels of camera variation, and considered traffic sign shapes on the classification performance, as well as background feature importance. [...] Results include a quantification of when and how much background features gain importance to support the classification task based on changes in the training domain [...]. Download: synset.de/datasets/synset-signset-ger/background-effect
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。