.png){kind=icon}
返回
Dead pixel test using effective receptive field
.png){kind=icon}
OA
AI
DOI：10.1016/j.patrec.2023.02.018.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep neural networks have been used in various fields, but their internal behavior in how they under- stand images is not well known. In this study, we discuss two counterintuitive properties of convolutional neural networks (CNNs). First, we evaluated the size of the receptive field of CNNs with their classification accuracy. Previous studies have attempted to increase the size of the receptive field for performance gain. However, we observed that some CNNs with a smaller receptive field can achieve higher classification accuracy. In this regard, we claim that a larger receptive field does not guarantee improved classification accuracy. Second, using the effective receptive field, we examined the contribution of each pixel to the output of CNN. Intuitively, each pixel is expected to equally contribute to the final output, but we found that there exist pixels in a partially dead state with little contribution to the output. We reveal that the reason for dead pixels lies in even stride operations with odd-sized kernels in CNN and propose a kernel padding method to remove the dead pixels. We demonstrated the vulnerability of CNNs with dead pix- els when we detect a noise or small box that is on dead pixels. Our findings on dead pixels should be understood and considered in practical applications of CNN.(c) 2023 Elsevier B.V. All rights reserved.
Keyword:
Convolutional neural networks
Receptive field
Convolutional kernel
Model interpretation
Computer vision
Deep learning
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:
3.3
论文数:
8.0K
被引数:
1.6W
机构
暂无机构信息
引用论文
.png){kind=icon}
分享收藏Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationGrad-cam: 通过基于梯度的定位从深度网络进行视觉解释OAAI
OAAI分享收藏 没有更多内容
没有更多内容