Paper Info
Title
Element-Wise Feature Relation Learning Network for Cross-Spectral Image Patch Matching
Abstract
Recently, the majority of successful matching approaches are based on convolutional neural networks, which focus on learning the invariant and discriminative features for individual image patches based on image content. However, the image patch matching task is essentially to predict the matching relationship of patch pairs, that is, matching (similar) or non-matching (dissimilar). Therefore, we consider that the feature relation (FR) learning is more important than individual feature learning for image patch matching problem. Motivated by this, we propose an element-wise FR learning network for image patch matching, which transforms the image patch matching task into an image relationship-based pattern classification problem and dramatically improves generalization performances on image matching. Meanwhile, the proposed element-wise learning methods encourage full interaction between feature information and can naturally learn FR. Moreover, we propose to aggregate FR from multilevels, which integrates the multiscale FR for more precise matching. Experimental results demonstrate that our proposal achieves superior performances on cross-spectral image patch matching and single spectral image patch matching, and good generalization on image patch retrieval.
Year
DOI
Venue
2022
10.1109/TNNLS.2021.3052756
IEEE Transactions on Neural Networks and Learning Systems
Keywords
DocType
Volume
Aggregated features,element-wise,feature learning,image matching,patch matching,relation learning
Journal
33
Issue
ISSN
Citations 
8
2162-237X
0
PageRank 
References 
Authors
0.34
20
8
Name
Order
Citations
PageRank
Dou Quan123.06
Shuang Wang231639.83
Ning Huyan3102.79
Jocelyn Chanussot44145272.11
Ruojing Wang502.03
Xuefeng Liang611415.43
Biao Hou736849.04
Licheng Jiao85698475.84