研究图表编码如何影响视觉模型的偏见，揭示设计细节会误导模型学习。
VEIL: How Visual Encoding Hijacking Induces Bias In Vision Models
- 通过相似性、可迁移性与归因分析，系统检验图表编码对模型的影响。
- 注意力训练仅在编码敏感时有效，否则效果有限或适得其反。
- 适合关注可视化设计与模型公平性的研究人员参考。
将时间序列渲染为图表图像用于基于CNN的分类在时间序列分类（TSC）中日益普遍。然而，尚不清楚模型是学习了底层时间模式，还是依赖于图表设计引入的特定视觉线索。我们提出VEIL：一项系统性研究，通过相似性、可迁移性和归因分析，考察图表编码如何影响学习表征。当诊断中一致识别出编码敏感性时，注意力引导训练可缓解该效应；但若此类信号缺失，则效果有限甚至产生负向影响。这些发现将VEIL置于机器如何感知可视化这一更广泛问题之中，拓展了图形感知的研究范畴——从人类读者延伸至视觉模型。结果表明，可视化设计选择会以值得重视的方式塑造学习表征，因此应将基于图表的TSC视为表示与测量问题，而非简单的建模决策。
原文摘要 · Abstract (English)
Rendering time series as chart images for CNN-based classification has become increasingly common in time-series classification (TSC). However, it remains unclear whether models learn underlying temporal patterns or rely on encoding-specific visual cues introduced by chart design. We present VEIL: a systematic study examining how chart encodings influence learned representations through complementary analyses of similarity, transferability, and attribution. Attention-guided training appears to mitigate this effect when encoding sensitivity is consistently identified across diagnostics, but provides limited or negative benefit when such signals are absent. These findings position VEIL within the broader question of how machines perceive visualizations -- extending graphical perception from human readers to vision models -- and show that visualization design choices shape learned representations in ways that warrant treating chart-based TSC as a representation and measurement problem rather than a simple modeling decision.
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。