Multi-Relation Attention Network for Image Patch Matching
Autor: | Licheng Jiao, Bowu Yang, Ning Huyan, Biao Hou, Yi Li, Jocelyn Chanussot, Dou Quan, Shuang Wang |
---|---|
Přispěvatelé: | Xidian University, GIPSA - Signal Images Physique (GIPSA-SIGMAPHY), GIPSA Pôle Sciences des Données (GIPSA-PSD), Grenoble Images Parole Signal Automatique (GIPSA-lab), Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA)-Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Grenoble Alpes (UGA), Institut National de Recherche en Informatique et en Automatique (Inria), ANR-19-P3IA-0003,MIAI,MIAI @ Grenoble Alpes(2019), Apprentissage de modèles à partir de données massives (Thoth), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ) |
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Matching (statistics)
Relation (database) Image matching Computer science business.industry Deep learning Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition 02 engineering and technology Computer Graphics and Computer-Aided Design Convolutional neural network attention learning Feature (computer vision) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence feature relations business Image retrieval [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing Software Similarity learning ComputingMilieux_MISCELLANEOUS |
Zdroj: | IEEE Transactions on Image Processing IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2021, 30, pp.7127-7142. ⟨10.1109/TIP.2021.3101414⟩ IEEE Transactions on Image Processing, 2021, 30, pp.7127-7142. ⟨10.1109/TIP.2021.3101414⟩ |
ISSN: | 1057-7149 |
Popis: | International audience; Deep convolutional neural networks attract increasing attention in image patch matching. However, most of them rely on a single similarity learning model, such as feature distance and the correlation of concatenated features. Their performances will degenerate due to the complex relation between matching patches caused by various imagery changes. To tackle this challenge, we propose a multi-relation attention learning network (MRAN) for image patch matching. Specifically, we propose to fuse multiple feature relations (MR) for matching, which can benefit from the complementary advantages between different feature relations and achieve significant improvements on matching tasks. Furthermore, we propose a relation attention learning module to learn the fused relation adaptively. With this module, meaningful feature relations are emphasized and the others are suppressed. Extensive experiments show that our MRAN achieves best matching performances, and has good generalization on multi-modal image patch matching, multi-modal remote sensing image patch matching and image retrieval tasks. |
Databáze: | OpenAIRE |
Externí odkaz: |