用生成模型修复图像分类中对背景的错误依赖。
Focusing Image Generation to Mitigate Spurious Correlations
- 基于预训练分类器误判区域生成新数据，削弱虚假关联。
- 在三个不同数据集上验证，显著降低分类器对背景的依赖。
- 无需标注虚假属性，可通用集成到其他去偏方法中。
图像中的实例特征与背景特征存在虚假相关性，影响深度神经网络分类器的训练过程，导致分类器对实例特征关注不足，引发错误分类。本文提出一种名为伪相关引导合成（SCGS）的数据增强方法，通过图像生成模型缓解虚假相关性。该方法无需为训练数据标注昂贵的伪相关属性（组），且可广泛应用于其他去偏方法。具体而言，SCGS首先识别预训练分类器在训练图像上的错误注意力区域，随后利用图像生成模型基于这些区域生成新的训练数据，从而增加数据多样性与规模，减轻虚假相关性对分类器的影响。分类器注意力区域的变化及在三个不同领域数据集上的实验结果表明，该方法能有效减少分类器对虚假相关性的依赖。
原文摘要 · Abstract (English)
Instance features in images exhibit spurious correlations with background features, affecting the training process of deep neural classifiers. This leads to insufficient attention to instance features by the classifier, resulting in erroneous classification outcomes. In this paper, we propose a data augmentation method called Spurious Correlations Guided Synthesis (SCGS) that mitigates spurious correlations through image generation model. This approach does not require expensive spurious attribute (group) labels for the training data and can be widely applied to other debiasing methods. Specifically, SCGS first identifies the incorrect attention regions of a pre-trained classifier on the training images, and then uses an image generation model to generate new training data based on these incorrect attended regions. SCGS increases the diversity and scale of the dataset to reduce the impact of spurious correlations on classifiers. Changes in the classifier's attention regions and experimental results on three different domain datasets demonstrate that this method is effective in reducing the classifier's reliance on spurious correlations.
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。