用人类视觉注意力指导神经网络，让模型决策更可解释。
Increasing Interpretability of Neural Networks By Approximating Human Visual Saliency
- 结合人类视觉显著性与主动学习，减少80%人工标注。
- 加入显著性信息后，模型可解释性最高提升30%。
- 适合需要高可解释性的医疗、自动驾驶等场景。
理解模型在图像中关注的具体位置，对提升决策过程的人类可解释性至关重要。基于深度学习的方案容易学习训练数据中的偶然关联，导致过拟合并降低可解释性。近期研究表明，引导模型关注单张图像中人类定义的显著区域，能显著提升性能和可解释性。此类模型还展现出更强的泛化能力，因避免了数据集中的偶然特征。实验表明，融入显著性信息的模型可解释性相比无显著性信息的模型最高提升30%。然而，收集显著性信息成本高、耗时且在某些情况下不可行。为解决此问题，我们提出一种显著性融合与主动学习相结合的策略，在保持可解释性和性能提升的前提下，将所需人工标注数据减少80%。大量实验验证了该方法在五个公开数据集和六种主动学习准则下的有效性。
原文摘要 · Abstract (English)
Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets, causing over-fitting and reducing the explainability. Recent advances have shown that guiding models to human-defined regions of saliency within individual images significantly increases performance and interpretability. Human-guided models also exhibit greater generalization capabilities, as coincidental dataset features are avoided. Results show that models trained with saliency incorporation display an increase in interpretability of up to 30% over models trained without saliency information. The collection of this saliency information, however, can be costly, laborious and in some cases infeasible. To address this limitation, we propose a combination strategy of saliency incorporation and active learning to reduce the human annotation data required by 80% while maintaining the interpretability and performance increase from human saliency. Extensive experimentation outlines the effectiveness of the proposed approach across five public datasets and six active learning criteria.
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。