期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 33, 期 12, 页码 7913-7920出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2021.3084633
关键词
Convolutional codes; Biological neural networks; Neurons; Convolution; Task analysis; Feature extraction; Image retrieval; Content-based image retrieval (CBIR); convolution neural networks; deep learning; image processing; image retrieval
类别
资金
- Polish National Science Centre [2017/27/B/ST6/02852]
In this brief, a novel algorithm is proposed for constructing effective descriptors for content-based image retrieval using deep neural networks. The descriptors made up of values from both fully connected and convolutional layers perfectly represent the entire image content. Experimental verification showed the effectiveness of these descriptors in semantic matching and secondary image characteristics.
In this brief, we consider the problem of descriptors construction for the task of content-based image retrieval using deep neural networks. The idea of neural codes, based on fully connected layers' activations, is extended by incorporating the information contained in convolutional layers. It is known that the total number of neurons in the convolutional part of the network is large and the majority of them have little influence on the final classification decision. Therefore, in this brief, we propose a novel algorithm that allows us to extract the most significant neuron activations and utilize this information to construct effective descriptors. The descriptors consisting of values taken from both the fully connected and convolutional layers perfectly represent the whole image content. The images retrieved using these descriptors match semantically very well to the query image, and also, they are similar in other secondary image characteristics, such as background, textures, or color distribution. These features of the proposed descriptors are verified experimentally based on the IMAGENET1M dataset using the VGG16 neural network. For comparison, we also test the proposed approach on the ResNet50 network.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据