人类对齐的深度学习：可解释性、因果性与生物学启发
Human-aligned Deep Learning: Explainability, Causality, and Biological Inspiration
AI总结：
本研究从可解释性、因果性和生物视觉三视角将深度学习与人类推理对齐，提出相关框架与模型，提升图像分类的效率、可解释性与鲁棒性，推动其临床应用。
摘要：
本研究将深度学习（DL）与人类推理能力和需求对齐，以实现更高效、可解释且鲁棒的图像分类。我们从可解释性、因果性和生物视觉三个视角展开研究。在深入探讨操作章节前，先介绍研究背景。首先，我们评估了医学图像的神经网络可视化技术，并验证了一种用于乳腺肿块分类的“设计即解释”方法。随后，我们对可解释人工智能（XAI）与因果性交叉领域进行全面综述，提出一个通用框架来组织过往及未来研究，为第二个视角奠定基础。在因果性方向，我们提出利用医学图像特征共现的新型模块，以实现更有效且可解释的预测；进一步引入CROCODILE框架，整合因果概念、对比学习、特征解耦和先验知识以增强泛化能力。最后，我们探索生物视觉，研究人类识别物体的方式，并提出CoCoReco——一种具有上下文感知注意力机制的连接性启发网络。总体而言，我们的关键发现包括：（1）简单的激活最大化对医学成像DL模型缺乏洞察力；（2）原型部分学习有效且与放射学对齐；（3）XAI与因果机器学习（ML）深度关联；（4）无需先验信息即可利用弱因果信号提升性能和可解释性；（5）框架在医学领域和分布外数据中具有泛化性；（6）整合生物电路基序可改善人类对齐的识别。本研究推动了人类对齐的DL发展，为弥合研究与临床应用的差距提供了路径，对提升信任度、诊断准确性和安全部署具有重要意义。
英文摘要：
This work aligns deep learning (DL) with human reasoning capabilities and needs to enable more efficient, interpretable, and robust image classification. We approach this from three perspectives: explainability, causality, and biological vision. Introduction and background open this work before diving into operative chapters. First, we assess neural networks' visualization techniques for medical images and validate an explainable-by-design method for breast mass classification. A comprehensive review at the intersection of XAI and causality follows, where we introduce a general scaffold to organize past and future research, laying the groundwork for our second perspective. In the causality direction, we propose novel modules that exploit feature co-occurrence in medical images, leading to more effective and explainable predictions. We further introduce CROCODILE, a general framework that integrates causal concepts, contrastive learning, feature disentanglement, and prior knowledge to enhance generalization. Lastly, we explore biological vision, examining how humans recognize objects, and propose CoCoReco, a connectivity-inspired network with context-aware attention mechanisms. Overall, our key findings include: (i) simple activation maximization lacks insight for medical imaging DL models; (ii) prototypical-part learning is effective and radiologically aligned; (iii) XAI and causal ML are deeply connected; (iv) weak causal signals can be leveraged without a priori information to improve performance and interpretability; (v) our framework generalizes across medical domains and out-of-distribution data; (vi) incorporating biological circuit motifs improves human-aligned recognition. This work contributes toward human-aligned DL and highlights pathways to bridge the gap between research and clinical adoption, with implications for improved trust, diagnostic accuracy, and safe deployment.
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。
