用简单是/否标注纠正模型注意力，提升推理准确性
Effective Guidance for Model Attention with Simple Yes-no Annotations
- 仅需是/否标注，通过简单反馈修正模型关注区域
- 在3个数据集上超越12种方法，达到当前最佳性能
- 适合希望低成本优化模型解释性的研究者和工程师
现代深度学习模型常关注无关区域，导致预测偏差和泛化能力受限。现有方法需标注无关区域或像素级注意力真值，成本高。本文提出CRAYON（Correcting Reasoning with Annotations of Yes Or No），利用简单的是/否标注，有效、可扩展且实用地修正模型注意力。CRAYON-ATTENTION基于显著性图引导经典解释方法聚焦相关图像区域；CRAYON-PRUNING则通过概念识别方法剔除无关神经元以降低其影响。通过大量定量与人工评估，验证了其有效性、可扩展性与实用性。在3个基准数据集上，优于12种方法，超越依赖复杂标注的方案。
原文摘要 · Abstract (English)
Modern deep learning models often make predictions by focusing on irrelevant areas, leading to biased performance and limited generalization. Existing methods aimed at rectifying model attention require explicit labels for irrelevant areas or complex pixel-wise ground truth attention maps. We present CRAYON (Correcting Reasoning with Annotations of Yes Or No), offering effective, scalable, and practical solutions to rectify model attention using simple yes-no annotations. CRAYON empowers classical and modern model interpretation techniques to identify and guide model reasoning: CRAYON-ATTENTION directs classic interpretations based on saliency maps to focus on relevant image regions, while CRAYON-PRUNING removes irrelevant neurons identified by modern concept-based methods to mitigate their influence. Through extensive experiments with both quantitative and human evaluation, we showcase CRAYON's effectiveness, scalability, and practicality in refining model attention. CRAYON achieves state-of-the-art performance, outperforming 12 methods across 3 benchmark datasets, surpassing approaches that require more complex annotations.
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。