.png){kind=icon}
返回
Visualizing and analyzing convolution neural networks with gradient information
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2018.02.080.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, convolution neural networks (CNNs) have demonstrated state-of-the-art results on image classification. However, our understanding of how they work is still limited. This paper expands the gradient-based visualization method by emphasizing the ability of CNNs in extracting local features, visualizes and analyzes the internal behavior of trained CNNs based on computing the gradient of the class score with respect to every layer of CNNs. Besides, we use a quantitative evaluation named prediction difference to verify the proposed visualization method. The saliency maps constructed from different layers demonstrate what CNNs care about in input images and it turns out that when CNNs classify an image, they identify the location of the object. Finally, we compare AlexNet with VGGnets, all of them have the same focus on the input images and VGGnets are more sensitive to pixels. (c) 2018 Elsevier B.V. All rights reserved.
Keyword:
CNNs
Visualization
Gradient
Receptive field
Prediction difference
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Hybrid recursive least squares algorithm for online sequential identification using data chunks基于数据块的在线顺序辨识的混合递推最小二乘算法.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏分享收藏X-ray investigation of the coordination and complex formation of lanthanoid ions in aqueous perchlorate and selenate solutions高氯酸盐和硒酸水溶液中镧系离子的配位和络合物形成的x射线研究
PREAI
分享收藏 没有更多内容
没有更多内容