基于Token的视觉Transformer虚假相关性检测
Token-Based Detection of Spurious Correlations in Vision Transformers
AI总结：
本研究提出基于Token的诊断流程，通过留一Token移除法检测视觉Transformer中的虚假相关性，经ImageNet等实验验证了方法的有效性，还探讨了虚假信号的来源及相关案例。
摘要：
基于神经网络的计算机视觉模型凭借强大的特征关联能力，能够检测并利用数据中意外存在的模式，可能依据错误或非预期但统计相关的信号做出正确预测。这些线索范围从简单的颜色偏差到图像中的小块文本不等。当这些意外信号与预测任务对齐时，模型可能会错误地将这些特征与任务关联，并依赖它们进行预测，这种现象被称为虚假相关性——即看似与任务相关实则为巧合的模式。因此，虚假相关性的检测与缓解已成为构建可信、可靠且可泛化的机器学习模型的关键任务。本研究提出一种基于Token的诊断流程，该流程应用留一Token移除法来检测视觉Transformer中的虚假相关性。所提方法通过互补度量来量化模型对非核心视觉线索的依赖，这些度量可在Token级别捕捉聚合和局部的虚假效应。我们在ImageNet数据集上对监督式和自监督式训练的模型开展大规模实验，证明所提方法识别虚假相关性的能力。我们还发现，即便使用相同的架构，训练方法对模型对虚假相关性的依赖也有显著影响。此外，我们表明对于某些ImageNet类别，多个模型的大量图像都表现出对非核心视觉线索的强依赖，并讨论此类信号的常见来源（例如水印和背景伪影）。最后，我们开展一项案例研究，探究浸润性乳腺肿块分类中的虚假信号。
英文摘要：
Due to their powerful feature association capabilities, neural network-based computer vision models have the ability to detect and exploit unintended patterns within the data, potentially leading to correct predictions based on incorrect or unintended but statistically relevant signals. These clues may vary from simple color aberrations to small pieces of text within the image. In situations where these unintended signals align with the predictive task, models can mistakenly link these features with the task and rely on them for making predictions. This phenomenon is referred to as spurious correlations, where patterns appear to be associated with the task but are actually coincidental. As a result, detection and mitigation of spurious correlations have become crucial tasks for building trustworthy, reliable, and generalizable machine learning models. In this work, we present a token-based diagnostic pipeline that applies leave-one-out token removal to detect spurious correlations in vision transformers. The proposed approach quantifies a model's reliance on non-core visual cues through complementary measures that capture both aggregate and localized spurious effects at the token level. Using both supervised and self-supervised trained models, we present large-scale experiments on the ImageNet dataset demonstrating the ability of the proposed method to identify spurious correlations. We also find that, even if the same architecture is used, the training methodology has a substantial impact on the model's reliance on spurious correlations. Furthermore, we show that for certain ImageNet classes, many images exhibit strong reliance on non-core visual cues across multiple models, and we discuss common sources of such signals (e.g., watermarks and background artifacts). Lastly, we present a case study investigating spurious signals in invasive breast mass classification.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
