Harnessing edge-enhanced attention mechanisms for supernova detection in deep learning frameworks
文献类型：期刊论文
| 作者 | Yin, K.3; Jia, J.2,3; Li, F.3; Gao, X.1; Sun, T.4 |
| 刊名 | ASTRONOMY AND COMPUTING
 |
| 出版日期 | 2024 |
| 卷号 | 46页码:100784 |
| 关键词 | Object detection Edge attention Data augmentation Supernova detection Sky survey |
| ISSN号 | 2213-1337 |
| DOI | 10.1016/j.ascom.2023.100784 |
| 产权排序 | 3 |
| 英文摘要 | Recent studies have shown the advantages of convolutional neural networks in the classification and detection of supernovae. In our prior work, we employed one-stage object detection frameworks to address the challenges of presupposed location and varying image sizes in supernova detection. Notably, the backbone of the object detectors naturally emphasized the edges of candidate regions in the visualized heatmap, reflecting the strategies adopted by human observers. Capitalizing on this similarity, we introduce an innovative edge attention module, tailored to prioritize the edges of candidate regions, and improved the performance of supernova detectors. In parallel, we have developed a three-channel supernova detection dataset by integrating science (current), template (reference), and difference images into a three-channel configuration. The candidates in the new dataset are more conspicuous. To assess the efficacy of our edge attention module, we conducted a series of experiments on the proposed dataset. The experimental results establish the superiority of the proposed method in detecting supernovae. Additionally, visualizations of the feature maps shows the proposed edge attention is able to reallocate weights around the candidate edges, corroborating its effectiveness. |
| WOS关键词 | SYNOPTIC SURVEY TELESCOPE |
| WOS研究方向 | Astronomy & Astrophysics ; Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001147346500001 |
| 出版者 | ELSEVIER |
| 源URL | [http://ir.xao.ac.cn/handle/45760611-7/5740]  |
| 专题 | 研究单元未命名 |
| 通讯作者 | Yin, K. |
| 作者单位 | 1.Chinese Acad Sci, Xinjiang Astron Observ, Urumqi 830011, Xinjiang, Peoples R China 2.Collaborat Innovat Ctr Novel Software Technol & In, Nanjing 210000, Jiangsu, Peoples R China 3.Soochow Univ, Sch Comp Sci & Technol, Suzhou 215006, Jiangsu, Peoples R China 4.Chinese Acad Sci, Purple Mt Observ, Nanjing 210023, Jiangsu, Peoples R China |
| 推荐引用方式 GB/T 7714 | Yin, K.,Jia, J.,Li, F.,et al. Harnessing edge-enhanced attention mechanisms for supernova detection in deep learning frameworks[J]. ASTRONOMY AND COMPUTING,2024,46:100784. |
| APA | Yin, K.,Jia, J.,Li, F.,Gao, X.,&Sun, T..(2024).Harnessing edge-enhanced attention mechanisms for supernova detection in deep learning frameworks.ASTRONOMY AND COMPUTING,46,100784. |
| MLA | Yin, K.,et al."Harnessing edge-enhanced attention mechanisms for supernova detection in deep learning frameworks".ASTRONOMY AND COMPUTING 46(2024):100784. |
入库方式： OAI收割
来源：新疆天文台
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。