提出新指标揭示图像模型依赖纹理而非形状，解释真实场景下误判原因
Err on the Side of Texture: Texture Bias on Real Data
- 引入纹理关联值TAV量化模型对特定纹理的依赖程度
- 发现90%自然对抗样本因纹理与真实标签不匹配导致错误分类
- 适合关注模型鲁棒性与可解释性的研究者阅读
偏差严重损害机器学习模型的准确性和可信度。目前在图像分类模型中观察到最强烈的偏差之一是纹理偏差——模型过度依赖纹理信息而非形状信息。然而，现有测量和缓解纹理偏差的方法尚未能捕捉纹理如何影响真实场景下的模型鲁棒性。本文提出纹理关联值（TAV），一种新型指标，用于量化模型在分类物体时对特定纹理存在的依赖强度。基于TAV，我们证明模型的准确性和鲁棒性受纹理显著影响。结果表明，纹理偏差解释了自然对抗样本的存在：超过90%的此类样本包含与真实标签学习纹理不匹配的纹理，导致模型产生高置信度误判。
原文摘要 · Abstract (English)
Bias significantly undermines both the accuracy and trustworthiness of machine learning models. To date, one of the strongest biases observed in image classification models is texture bias-where models overly rely on texture information rather than shape information. Yet, existing approaches for measuring and mitigating texture bias have not been able to capture how textures impact model robustness in real-world settings. In this work, we introduce the Texture Association Value (TAV), a novel metric that quantifies how strongly models rely on the presence of specific textures when classifying objects. Leveraging TAV, we demonstrate that model accuracy and robustness are heavily influenced by texture. Our results show that texture bias explains the existence of natural adversarial examples, where over 90% of these samples contain textures that are misaligned with the learned texture of their true label, resulting in confident mispredictions.
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。