机构
*
Network Analysis and Social Influence Modelling (NASIM) Lab(网络分析与社会影响建模实验室)
;
School of Physics Maths and Computing, The University of Western Australia(西澳大学物理数学与计算学院)
;
School of Psychological Science, The University of Western Australia(西澳大学心理学科学学院)
;
School of Computing, Macquarie University(麦考瑞大学计算机学院)
SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability
SPARC:概念对齐的稀疏自编码器用于跨模型和跨模态可解释性
Ali Nasiri-Sarvi, Hassan Rivaz, Mahdi S. Hosseini
机构
*
Department of Computer Science and Software Engineering (CSSE) Concordia University, Canada(计算机科学与软件工程系(CSSE)康科迪亚大学,加拿大)
;
Department of Electrical and Computer Engineering (ECE) Concordia University, Canada(电气与计算机工程系(ECE)康科迪亚大学,加拿大)
FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI
FunnyNodules: 一种可定制的医学数据集,用于评估可解释AI
Luisa Gallée, Yiheng Xiong, Meinrad Beer, Michael Götz
机构
*
Ulm University Medical Center(乌尔姆大学医学中心)
;
XAIRAD - Cooperation for Artificial Intelligence in Experimental Radiology(XAIRAD——实验放射学人工智能合作)
;
Department of Diagnostic and Interventional Radiology(诊断与介入放射学系)
专题命中
其他安全
:alignment(abstract)
AI总结
FunnyNodules是一种可定制的医学数据集,用于评估可解释AI模型的属性推理能力。
Commentsaccepted at Medical Imaging with Deep Learning (MIDL) 2026