Examination of the Relationship between Feature Extraction by Kernels and CNN Performance

被引：0

作者：

Togawa, Sora ^{[1
]}

Jin'no, Kenya ^{[1
]}

机构：

[1] Tokyo City Univ, Fac Informat Technol, Tokyo, Japan

来源：

2024 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS 2024 | 2024年

关键词：

CNN; Explainable AI; Feature Extraction; Filter; Frequency Analysis; Image Recognition; Kernel;

D O I：

10.1109/ISCAS58744.2024.10557842

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Convolutional Neural Networks (CNNs) excel at various image-related tasks. These networks extract local features from images using small-sized kernels. By stacking multiple convolutional layers, they can not only focus on local regions but also capture broader global features of the input image. In this article, we'll examine the kernels learned by various CNNs to understand the features they extract. We'll also assess the significance of these kernels and discuss how they relate to the CNN's performance.

引用

页数：5

共 50 条

[31] Chinese Character Recognition Based on Gabor Feature Extraction and CNN
Xiong Yudian
Lu Tongwei
Jiang Yongyuan
MIPPR 2017: PATTERN RECOGNITION AND COMPUTER VISION, 2017, 10609
[32] Fusion of CNN and Feature Extraction Methods for Multiple Sclerosis Classification
Souid, Bouthaina
Yahia, Samah
Bouchrika, Tahani
Jemai, Olfa
FIFTEENTH INTERNATIONAL CONFERENCE ON MACHINE VISION, ICMV 2022, 2023, 12701
[33] Feature extraction of postage stamps using an iterative approach of CNN
Kishida, J
Rekeczky, C
Nishio, Y
Ushida, A
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 1996, E79A (10) : 1741 - 1746
[34] Fingerprint feature extraction via CNN with Von Neumann neighborhood
Lou, Yijun
Chen, Fangyue
Guan, Junbiao
INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2007, 17 (11): : 4145 - 4151
[35] Fingerprint Feature Extraction Using CNN with Multiple Attention Mechanisms
Sasuga, Nagisa
Ito, Koichi
Aoki, Takafumi
2022 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS (IJCB), 2022,
[36] Feature Extraction using CNN for Peripheral Blood Cells Recognition
Ammar, Mohammed
Daho, Mostafa El Habib
Harrar, Khaled
Laidi, Amel
EAI ENDORSED TRANSACTIONS ON SCALABLE INFORMATION SYSTEMS, 2022, 9 (34):
[37] On the Use of Different Feature Extraction Methods for Linear and Non Linear kernels
Trabelsi, Imen
Ben Ayed, Dorra
2012 6TH INTERNATIONAL CONFERENCE ON SCIENCES OF ELECTRONICS, TECHNOLOGIES OF INFORMATION AND TELECOMMUNICATIONS (SETIT), 2012, : 797 - 802
[38] Laplacian discriminant projection with optimized Kernels for supervised feature extraction and classification
Li, Jun-Bao
Chu, Shu-Chuan
Pan, Jeng-Shyang
PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, 2007, : 115 - +
[39] Dual-Stream Feature Extraction Network Based on CNN and Transformer for Building Extraction
Xia, Liegang
Mi, Shulin
Zhang, Junxia
Luo, Jiancheng
Shen, Zhanfeng
Cheng, Yubin
REMOTE SENSING, 2023, 15 (10)
[40] An examination of the relationship between conscientiousness and citizenship performance and task performance, within an academic setting
Poropat, A
AUSTRALIAN JOURNAL OF PSYCHOLOGY, 2004, 56 : 150 - 150

← 1 2 3 4 5 →