.png){kind=icon}
返回
Transform Domain Learning for Image Recognition
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3432670.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Image and video classification are distinct tasks in computer vision. Three-dimensional convolutional neural networks (3D CNNs) are commonly employed for video classification, while two-dimensional convolutional neural networks (2D CNNs) are more suitable for image classification. To enable image and video recognition to adopt the same network-3D CNNs, we propose a transform domain learning approach for image recognition utilizing the video recognition model 3D CNNs. The transform domain learning not only permits the use of RGB images as input for 3D CNNs but also allows for the input of orthogonally transformed image sequences into the networks. Furthermore, randomly transformed images can be fed into the networks, where the random transformation is a customized arbitrary transformation. The standard 3D CNNs can be seamlessly applied to both images and videos. The experiments show that whether orthogonal transformation or random transformation is used as the input, 3D CNNs can effectively classify images. Compared to 2D CNNs, the data after orthogonal transformation does not reduce the accuracy. To unify the tasks of image and video classification, the image dataset Caltech101 and the video dataset UCF101 are mixed, and 3D CNNs are used to recognize images in the transform domain. The results illustrate that mixed and individual training produce almost the same recognition effect. Additionally, it can be observed that directly transferring the video pre-training model to the image classification task can significantly enhance the performance.
Keyword:
Transforms
Image recognition
Task analysis
Kernel
Three-dimensional displays
Solid modeling
Convolutional neural networks
Videos
Convolutional neural network
image recognition
orthogonal transformation
video recognition
期刊
IF:
3.6
论文数:
9.8W
被引数:
34.5W
机构
引用论文
An Efficient Methodology for Brain MRI Classification Based on DWT and Convolutional Neural Network一种基于DWT和卷积神经网络的高效脑MRI分类方法.png)
SENSORS
OAAI
SENSORSIF3.5
OAAI分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Research on the Efficiency of Wireless Power Transfer System Based on Multi-Auxiliary Transmitting Coils基于多辅助发射线圈的无线电能传输系统效率研究
PREAI
分享收藏Structural study of lanthanides(III) in aqueous nitrate and chloride solutions by EXAFS通过EXAFS对硝酸盐和氯化物水溶液中镧系元素 (III) 的结构研究
PREAI
分享收藏An Effective Hyperspectral Image Classification Approach Based on Discrete Wavelet Transform and Dense CNN基于离散小波变换和密集CNN的高光谱图像分类方法
PREAI
分享收藏
查看更多内容