Please use this identifier to cite or link to this item: https://scidar.kg.ac.rs/handle/123456789/15949
Title: Local Semantic Correlation Modeling Over Graph Neural Networks for Deep Feature Embedding and Image Retrieval
Authors: Kan S.
Cen Y.
Li, Yidong
Mladenovic, Vladimir
He Z.
Issue Date: 2022
Abstract: 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.
URI: https://scidar.kg.ac.rs/handle/123456789/15949
Type: article
DOI: 10.1109/TIP.2022.3163571
ISSN: 1057-7149
SCOPUS: 2-s2.0-85127747878
Appears in Collections:Faculty of Technical Sciences, Čačak

Page views(s)

47

Downloads(s)

1

Files in This Item:
File Description SizeFormat 
PaperMissing.pdf
  Restricted Access
29.86 kBAdobe PDFThumbnail
View/Open


Items in SCIDAR are protected by copyright, with all rights reserved, unless otherwise indicated.