模式识别(心理学)
人工智能
判别式
嵌入
计算机科学
特征(语言学)
边距(机器学习)
相关性
特征向量
图像检索
图形
图嵌入
人工神经网络
特征学习
特征提取
深度学习
图像(数学)
数学
机器学习
理论计算机科学
哲学
语言学
几何学
作者
Shichao Kan,Yigang Cen,Yang Li,Vladimir Mladenović,Zhihai He
出处
期刊:IEEE transactions on image processing
[Institute of Electrical and Electronics Engineers]
日期:2022-01-01
卷期号:31: 2988-3003
被引量:8
标识
DOI:10.1109/tip.2022.3163571
摘要
Deep feature embedding aims to learn discriminative features or feature embeddings for image samples which can minimize their intra-class distance while maximizing their inter-class distance. Recent state-of-the-art methods have been focusing on learning deep neural networks with carefully designed loss functions. In this work, we propose to explore a new approach to deep feature embedding. We learn a graph neural network to characterize and predict the local correlation structure of images in the feature space. Based on this correlation structure, neighboring images collaborate with each other to generate and refine their embedded features based on local linear combination. Graph edges learn a correlation prediction network to predict the correlation scores between neighboring images. Graph nodes learn a feature embedding network to generate the embedded feature for a given image based on a weighted summation of neighboring image features with the correlation scores as weights. Our extensive experimental results under the image retrieval settings demonstrate that our proposed method outperforms the state-of-the-art methods by a large margin, especially for top-1 recalls.
科研通智能强力驱动
Strongly Powered by AbleSci AI