Understanding Neural Network Systems for Image Analysis using Vector Spaces and Inverse Maps
Department of Computer Science（计算机科学系）；The University of California at Los Angeles（加州大学洛杉矶分校）；Department of Electrical and Computer Engineering（电气与计算机工程系）；The University of New Mexico, USA（新墨西哥大学）
Rebecca Pattichis, Marios S. Pattichis
备注：
Accepted to IEEE's Southwest Symposium on Image Analysis and Interpretation 2024
There is strong interest in developing mathematical methods that can be used to understand complex neural networks used in image analysis. In this paper, we introduce techniques from Linear Algebra to model neural network layers as maps between signal spaces. First, we demonstrate how signal spaces can be used to visualize weight spaces and convolutional layer kernels. We also demonstrate how residual vector spaces can be used to further visualize information lost at each layer. Second, we study invertible networks using vector spaces for computing input images that yield specific outputs. We demonstrate our approach on two invertible networks and ResNet18.
Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling
The Graduate Center of the City University of New York（纽约城市大学研究生中心）；Borough of Manhattan Community College - CUNY（纽约城市大学曼哈顿社区学院）；The City College of New York - CUNY（纽约城市大学纽约城市学院）
Understanding spatial correlation in eye-fixation maps for visual attention in videos
Georgia Institute of Technology（佐治亚理工学院）
在本文中，我们提出了一个分析记录的眼睛注视数据从人类受试者观看视频序列。目的是更好地理解视频的视觉注意力。利用CRCNS（Collaborative Research in Computational Neuroscience，计算神经科学合作研究）数据集提供的眼注视数据，在不对眼注视图的结构作任何假设的情况下，重点研究了像素的显著性与其直接相邻像素的显著性之间的关系。通过运用信息论中的一些基本概念，分析表明像素的显著性与其邻域的显著性之间存在着实质性的相关性。该分析还提供了对眼睛注视图的结构和动态的见解，这对于理解视频显著性及其应用非常有用。
Understanding the One-Pixel Attack: Propagation Maps and Locality Analysis
Faculty of Information Science and Electrical Engineering, Kyushu University（九州大学信息科学与电气工程学院）；Graduate School of Information Science and Electrical Engineering, Kyushu University（九州大学信息科学与电气工程研究生院）；Kyushu University（九州大学）
