CA-DDPM: Conditionally Embedded Attention-Aided Denoising Diffusion Probabilistic Model for High-Quality SAR Image Generation.
Saved in:
| Title: | CA-DDPM: Conditionally Embedded Attention-Aided Denoising Diffusion Probabilistic Model for High-Quality SAR Image Generation. |
|---|---|
| Authors: | Zheng, Yang1 (AUTHOR), Liu, Duhao1,2 (AUTHOR), Li, Ruimin2,3 (AUTHOR), Wang, Rongxu1 (AUTHOR), Fan, Junling2,3 (AUTHOR), Guo, Kaitai1,3 (AUTHOR), Liang, Jimin1 (AUTHOR) jimleung@mail.xidian.edu.cn |
| Source: | Remote Sensing. Jun2026, Vol. 18 Issue 12, p1994. 24p. |
| Subjects: | Synthetic aperture radar, Probabilistic generative models, Generative adversarial networks, Automatic target recognition, Data augmentation, Image quality in imaging systems, Deep learning |
| Abstract: | Highlights: What are the main findings? A novel conditionally embedded attention-aided denoising diffusion probabilistic model (CA-DDPM) is proposed for high-quality, multi-category SAR image generation. A comprehensive evaluation methodology is established to assess SAR image quality through the dimensions of authenticity, diversity, and utility in ATR tasks. What is the implication of the main finding? The established three-dimensional criteria provide a robust benchmark for quantitatively assessing the physical and semantic fidelity of synthetic SAR imagery. CA-DDPM produces more realistic and diverse SAR images than representative GANs and diffusion models, effectively enhancing downstream ATR performance. Deep learning-based automatic target recognition (ATR) for synthetic aperture radar (SAR) imagery requires large quantities of high-quality annotated data, yet real SAR samples are costly and difficult to obtain. Existing generative adversarial network (GAN)-based SAR generation methods often suffer from limited authenticity and insufficient diversity. To address these issues, we propose CA-DDPM, a conditionally embedded attention-aided denoising diffusion probabilistic model (DDPM) for high-quality multi-category SAR image generation. CA-DDPM employs a unified conditional embedding that fuses time-step and category information, injected into a U-Net backbone through a feature-wise linear modulation (FiLM)-based mechanism to achieve step-aware and class-aware denoising. Attention blocks are further incorporated to enhance the modeling of structural dependencies and fine scattering details. To evaluate generation quality, we develop a three-dimensional assessment framework that jointly examines authenticity, diversity, and utility in ATR. Authenticity is quantified using local and global similarity metrics under a unified Hungarian-matched statistical procedure, together with an SAR-adapted Fréchet inception distance (SAR-FID). Diversity is assessed through inter-category feature clustering, an SAR Inception Score (SAR-IS), and a newly proposed intra-category grayscale histogram-based metric. Utility is evaluated by hybrid training experiments across multiple ATR models. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset demonstrate that CA-DDPM produces more realistic and diverse SAR images than representative GAN- and DDPM-based baselines, and it effectively improves downstream ATR performance through data augmentation. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 194915127 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: CA-DDPM: Conditionally Embedded Attention-Aided Denoising Diffusion Probabilistic Model for High-Quality SAR Image Generation. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Zheng%2C+Yang%22">Zheng, Yang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Duhao%22">Liu, Duhao</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Ruimin%22">Li, Ruimin</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Rongxu%22">Wang, Rongxu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Fan%2C+Junling%22">Fan, Junling</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Guo%2C+Kaitai%22">Guo, Kaitai</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liang%2C+Jimin%22">Liang, Jimin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jimleung@mail.xidian.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Jun2026, Vol. 18 Issue 12, p1994. 24p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Synthetic+aperture+radar%22">Synthetic aperture radar</searchLink><br /><searchLink fieldCode="DE" term="%22Probabilistic+generative+models%22">Probabilistic generative models</searchLink><br /><searchLink fieldCode="DE" term="%22Generative+adversarial+networks%22">Generative adversarial networks</searchLink><br /><searchLink fieldCode="DE" term="%22Automatic+target+recognition%22">Automatic target recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Data+augmentation%22">Data augmentation</searchLink><br /><searchLink fieldCode="DE" term="%22Image+quality+in+imaging+systems%22">Image quality in imaging systems</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? A novel conditionally embedded attention-aided denoising diffusion probabilistic model (CA-DDPM) is proposed for high-quality, multi-category SAR image generation. A comprehensive evaluation methodology is established to assess SAR image quality through the dimensions of authenticity, diversity, and utility in ATR tasks. What is the implication of the main finding? The established three-dimensional criteria provide a robust benchmark for quantitatively assessing the physical and semantic fidelity of synthetic SAR imagery. CA-DDPM produces more realistic and diverse SAR images than representative GANs and diffusion models, effectively enhancing downstream ATR performance. Deep learning-based automatic target recognition (ATR) for synthetic aperture radar (SAR) imagery requires large quantities of high-quality annotated data, yet real SAR samples are costly and difficult to obtain. Existing generative adversarial network (GAN)-based SAR generation methods often suffer from limited authenticity and insufficient diversity. To address these issues, we propose CA-DDPM, a conditionally embedded attention-aided denoising diffusion probabilistic model (DDPM) for high-quality multi-category SAR image generation. CA-DDPM employs a unified conditional embedding that fuses time-step and category information, injected into a U-Net backbone through a feature-wise linear modulation (FiLM)-based mechanism to achieve step-aware and class-aware denoising. Attention blocks are further incorporated to enhance the modeling of structural dependencies and fine scattering details. To evaluate generation quality, we develop a three-dimensional assessment framework that jointly examines authenticity, diversity, and utility in ATR. Authenticity is quantified using local and global similarity metrics under a unified Hungarian-matched statistical procedure, together with an SAR-adapted Fréchet inception distance (SAR-FID). Diversity is assessed through inter-category feature clustering, an SAR Inception Score (SAR-IS), and a newly proposed intra-category grayscale histogram-based metric. Utility is evaluated by hybrid training experiments across multiple ATR models. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset demonstrate that CA-DDPM produces more realistic and diverse SAR images than representative GAN- and DDPM-based baselines, and it effectively improves downstream ATR performance through data augmentation. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194915127 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs18121994 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 24 StartPage: 1994 Subjects: – SubjectFull: Synthetic aperture radar Type: general – SubjectFull: Probabilistic generative models Type: general – SubjectFull: Generative adversarial networks Type: general – SubjectFull: Automatic target recognition Type: general – SubjectFull: Data augmentation Type: general – SubjectFull: Image quality in imaging systems Type: general – SubjectFull: Deep learning Type: general Titles: – TitleFull: CA-DDPM: Conditionally Embedded Attention-Aided Denoising Diffusion Probabilistic Model for High-Quality SAR Image Generation. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Zheng, Yang – PersonEntity: Name: NameFull: Liu, Duhao – PersonEntity: Name: NameFull: Li, Ruimin – PersonEntity: Name: NameFull: Wang, Rongxu – PersonEntity: Name: NameFull: Fan, Junling – PersonEntity: Name: NameFull: Guo, Kaitai – PersonEntity: Name: NameFull: Liang, Jimin IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 06 Text: Jun2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 18 – Type: issue Value: 12 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
