Metric networks for enhanced perception of non-local semantic information
Copyright © 2023 Li, Zhou and Zhang..
Introduction: Metric learning, as a fundamental research direction in the field of computer vision, has played a crucial role in image matching. Traditional metric learning methods aim at constructing two-branch siamese neural networks to address the challenge of image matching, but they often overlook to cross-source and cross-view scenarios.
Methods: In this article, a multi-branch metric learning model is proposed to address these limitations. The main contributions of this work are as follows: Firstly, we design a multi-branch siamese network model that enhances measurement reliability through information compensation among data points. Secondly, we construct a non-local information perception and fusion model, which accurately distinguishes positive and negative samples by fusing information at different scales. Thirdly, we enhance the model by integrating semantic information and establish an information consistency mapping between multiple branches, thereby improving the robustness in cross-source and cross-view scenarios.
Results: Experimental tests which demonstrate the effectiveness of the proposed method are carried out under various conditions, including homologous, heterogeneous, multi-view, and crossview scenarios. Compared to the state-of-the-art comparison algorithms, our proposed algorithm achieves an improvement of ~1, 2, 1, and 1% in terms of similarity measurement Recall10, respectively, under these four conditions.
Discussion: In addition, our work provides an idea for improving the crossscene application ability of UAV positioning and navigation algorithm.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:17 |
|---|---|
| Enthalten in: |
Frontiers in neurorobotics - 17(2023) vom: 15., Seite 1234129 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Li, Jia [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Cross-source |
|---|
| Anmerkungen: |
Date Revised 26.08.2023 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.3389/fnbot.2023.1234129 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM361203845 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM361203845 | ||
| 003 | DE-627 | ||
| 005 | 20231226084633.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.3389/fnbot.2023.1234129 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1203.xml |
| 035 | |a (DE-627)NLM361203845 | ||
| 035 | |a (NLM)37622128 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Li, Jia |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Metric networks for enhanced perception of non-local semantic information |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 26.08.2023 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Copyright © 2023 Li, Zhou and Zhang. | ||
| 520 | |a Introduction: Metric learning, as a fundamental research direction in the field of computer vision, has played a crucial role in image matching. Traditional metric learning methods aim at constructing two-branch siamese neural networks to address the challenge of image matching, but they often overlook to cross-source and cross-view scenarios | ||
| 520 | |a Methods: In this article, a multi-branch metric learning model is proposed to address these limitations. The main contributions of this work are as follows: Firstly, we design a multi-branch siamese network model that enhances measurement reliability through information compensation among data points. Secondly, we construct a non-local information perception and fusion model, which accurately distinguishes positive and negative samples by fusing information at different scales. Thirdly, we enhance the model by integrating semantic information and establish an information consistency mapping between multiple branches, thereby improving the robustness in cross-source and cross-view scenarios | ||
| 520 | |a Results: Experimental tests which demonstrate the effectiveness of the proposed method are carried out under various conditions, including homologous, heterogeneous, multi-view, and crossview scenarios. Compared to the state-of-the-art comparison algorithms, our proposed algorithm achieves an improvement of ~1, 2, 1, and 1% in terms of similarity measurement Recall10, respectively, under these four conditions | ||
| 520 | |a Discussion: In addition, our work provides an idea for improving the crossscene application ability of UAV positioning and navigation algorithm | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a cross-source | |
| 650 | 4 | |a cross-view | |
| 650 | 4 | |a multi-branch siamese network | |
| 650 | 4 | |a non-local information perception | |
| 650 | 4 | |a semantic information capture | |
| 700 | 1 | |a Zhou, Yu-Qian |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Qiu-Yan |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Frontiers in neurorobotics |d 2007 |g 17(2023) vom: 15., Seite 1234129 |w (DE-627)NLM184032342 |x 1662-5218 |7 nnns |
| 773 | 1 | 8 | |g volume:17 |g year:2023 |g day:15 |g pages:1234129 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.3389/fnbot.2023.1234129 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 17 |j 2023 |b 15 |h 1234129 | ||