Xiamen University（厦门大学）；Peng Cheng Laboratory（鹏城实验室）；National University of Singapore（新加坡国立大学）；Beihang University（北京航空航天大学）；BestImage, Tencent Technology (Shanghai) Co.,Ltd（腾讯科技（上海）有限公司）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
The remarkable performance of convolutional neural networks (CNNs) is entangled with their huge number of uninterpretable parameters, which has become the bottleneck limiting the exploitation of their full potential. Towards network interpretation, previous endeavors mainly resort to the single filter analysis, which however ignores the relationship between filters. In this paper, we propose a novel architecture decoupling method to interpret the network from a perspective of investigating its calculation paths. More specifically, we introduce a novel architecture controlling module in each layer to encode the network architecture by a vector. By maximizing the mutual information between the vectors and input images, the module is trained to select specific filters to distill a unique calculation path for each input. Furthermore, to improve the interpretability and compactness of the decoupled network, the output of each layer is encoded to align the architecture encoding vector with the constraint of sparsity regularization. Unlike conventional pixel-level or filter-level network interpretation methods, we propose a path-level analysis to explore the relationship between the combination of filter and semantic concepts, which is more suitable to interpret the working rationale of the decoupled network. Extensive experiments show that the decoupled network achieves several applications, i.e., network interpretation, network acceleration, and adversarial samples detection.
Volkswagen Group（大众集团）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Leibniz University Hannover（汉诺威莱布尼茨大学）；University of Applied Sciences Duesseldorf（杜塞尔多夫应用科学大学）
Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
Tsinghua National Lab for Information Science and Technology（清华大学信息科学与技术国家实验室）；State Key Lab of Intelligent Technology and Systems（智能技术与系统国家重点实验室）；Center for Bio-Inspired Computing Research（类脑计算研究中心）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
Euler-inspired Decoupling Neural Operator for Efficient Pansharpening
School of Software Technology, Zhejiang University（浙江大学软件技术学院）；School of Computer Science and Technology , Chongqing University of Post and Telecommunications（重庆邮电大学计算机科学与技术学院）
BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis
Emory University（埃默里大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Princeton University（普林斯顿大学）；Lehigh University（理海大学）
Explainable and Interpretable Diabetic Retinopathy Classification Based on Neural-Symbolic Learning
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Singapore Eye Research Institute（新加坡眼科研究所）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）；Institute for Molecular and Clinical Ophthalmology（分子与临床眼科研究所）；National University of Singapore（新加坡国立大学）
