CNN在小数据下过度聚焦局部特征，该文提出新正则化方法改善泛化能力。
The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach
- 用显著性图识别关键特征区域，训练时动态抑制其影响
- 实验显示模型注意力范围更广，泛化性能提升显著
- 适合关注模型可解释性与小样本学习的研究者
尽管变换器已成为计算机视觉的新标准，卷积神经网络（CNN）在低数据场景下仍表现更优。然而，当训练数据有限时，CNN常依赖输入图像的狭窄、特定区域进行决策，严重损害模型泛化能力，使其过度依赖某些可能不代表整体图像上下文的特征。本文旨在揭示这一现象并提出初步应对方案。为此，我们提出显著性引导丢弃（SGDrop），一种专门针对此问题的正则化方法。SGDrop利用特征图的归因方法识别最显著特征，并在训练中降低其影响，促使网络分散注意力，避免仅关注突出区域。在多个视觉分类基准上的实验验证了SGDrop在提升泛化能力方面的有效性。显著的是，采用SGDrop的模型展现出更广泛的归因分布和神经活动，相较于传统训练模型提供了对输入图像更全面的表征。
原文摘要 · Abstract (English)
Despite transformers being considered as the new standard in computer vision, convolutional neural networks (CNNs) still outperform them in low-data regimes. Nonetheless, CNNs often make decisions based on narrow, specific regions of input images, especially when training data is limited. This behavior can severely compromise the model's generalization capabilities, making it disproportionately dependent on certain features that might not represent the broader context of images. While the conditions leading to this phenomenon remain elusive, the primary intent of this article is to shed light on this observed behavior of neural networks. Our research endeavors to prioritize comprehensive insight and to outline an initial response to this phenomenon. In line with this, we introduce Saliency Guided Dropout (SGDrop), a pioneering regularization approach tailored to address this specific issue. SGDrop utilizes attribution methods on the feature map to identify and then reduce the influence of the most salient features during training. This process encourages the network to diversify its attention and not focus solely on specific standout areas. Our experiments across several visual classification benchmarks validate SGDrop's role in enhancing generalization. Significantly, models incorporating SGDrop display more expansive attributions and neural activity, offering a more comprehensive view of input images in contrast to their traditionally trained counterparts.
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。