用于伪装物体检测的去噪扩散隐含模型

IF 2.6 3区 工程技术 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS
Wei Cai, Weijie Gao, Xinhao Jiang, Xin Wang, Xingyu Di
{"title":"用于伪装物体检测的去噪扩散隐含模型","authors":"Wei Cai, Weijie Gao, Xinhao Jiang, Xin Wang, Xingyu Di","doi":"10.3390/electronics13183690","DOIUrl":null,"url":null,"abstract":"Camouflaged object detection (COD) is a challenging task that involves identifying objects that closely resemble their background. In order to detect camouflaged objects more accurately, we propose a diffusion model for the COD network called DMNet. DMNet formulates COD as a denoising diffusion process from noisy boxes to prediction boxes. During the training stage, random boxes diffuse from ground-truth boxes, and DMNet learns to reverse this process. In the sampling stage, DMNet progressively refines random boxes to prediction boxes. In addition, due to the camouflaged object’s blurred appearance and the low contrast between it and the background, the feature extraction stage of the network is challenging. Firstly, we proposed a parallel fusion module (PFM) to enhance the information extracted from the backbone. Then, we designed a progressive feature pyramid network (PFPN) for feature fusion, in which the upsample adaptive spatial fusion module (UAF) balances the different feature information by assigning weights to different layers. Finally, a location refinement module (LRM) is constructed to make DMNet pay attention to the boundary details. We compared DMNet with other classical object-detection models on the COD10K dataset. Experimental results indicated that DMNet outperformed others, achieving optimal effects across six evaluation metrics and significantly enhancing detection accuracy.","PeriodicalId":11646,"journal":{"name":"Electronics","volume":"40 1","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Denoising Diffusion Implicit Model for Camouflaged Object Detection\",\"authors\":\"Wei Cai, Weijie Gao, Xinhao Jiang, Xin Wang, Xingyu Di\",\"doi\":\"10.3390/electronics13183690\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Camouflaged object detection (COD) is a challenging task that involves identifying objects that closely resemble their background. In order to detect camouflaged objects more accurately, we propose a diffusion model for the COD network called DMNet. DMNet formulates COD as a denoising diffusion process from noisy boxes to prediction boxes. During the training stage, random boxes diffuse from ground-truth boxes, and DMNet learns to reverse this process. In the sampling stage, DMNet progressively refines random boxes to prediction boxes. In addition, due to the camouflaged object’s blurred appearance and the low contrast between it and the background, the feature extraction stage of the network is challenging. Firstly, we proposed a parallel fusion module (PFM) to enhance the information extracted from the backbone. Then, we designed a progressive feature pyramid network (PFPN) for feature fusion, in which the upsample adaptive spatial fusion module (UAF) balances the different feature information by assigning weights to different layers. Finally, a location refinement module (LRM) is constructed to make DMNet pay attention to the boundary details. We compared DMNet with other classical object-detection models on the COD10K dataset. Experimental results indicated that DMNet outperformed others, achieving optimal effects across six evaluation metrics and significantly enhancing detection accuracy.\",\"PeriodicalId\":11646,\"journal\":{\"name\":\"Electronics\",\"volume\":\"40 1\",\"pages\":\"\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2024-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Electronics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.3390/electronics13183690\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electronics","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.3390/electronics13183690","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

伪装物体检测(COD)是一项极具挑战性的任务,它涉及识别与其背景非常相似的物体。为了更准确地检测伪装物体,我们提出了一种名为 DMNet 的伪装物体检测网络扩散模型。DMNet 将 COD 表述为一个从噪声方框到预测方框的去噪扩散过程。在训练阶段,随机方框从地面实况方框扩散,而 DMNet 则学习逆转这一过程。在采样阶段,DMNet 逐步将随机方框细化为预测方框。此外,由于伪装物体外观模糊,与背景对比度低,网络的特征提取阶段具有挑战性。首先,我们提出了并行融合模块(PFM)来增强从骨干网中提取的信息。然后,我们设计了用于特征融合的渐进式特征金字塔网络(PFPN),其中的上采样自适应空间融合模块(UAF)通过为不同层分配权重来平衡不同的特征信息。最后,我们构建了一个位置细化模块(LRM),使 DMNet 能够关注边界细节。我们在 COD10K 数据集上比较了 DMNet 和其他经典物体检测模型。实验结果表明,DMNet 的表现优于其他模型,在六个评价指标上都达到了最佳效果,并显著提高了检测精度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Denoising Diffusion Implicit Model for Camouflaged Object Detection
Camouflaged object detection (COD) is a challenging task that involves identifying objects that closely resemble their background. In order to detect camouflaged objects more accurately, we propose a diffusion model for the COD network called DMNet. DMNet formulates COD as a denoising diffusion process from noisy boxes to prediction boxes. During the training stage, random boxes diffuse from ground-truth boxes, and DMNet learns to reverse this process. In the sampling stage, DMNet progressively refines random boxes to prediction boxes. In addition, due to the camouflaged object’s blurred appearance and the low contrast between it and the background, the feature extraction stage of the network is challenging. Firstly, we proposed a parallel fusion module (PFM) to enhance the information extracted from the backbone. Then, we designed a progressive feature pyramid network (PFPN) for feature fusion, in which the upsample adaptive spatial fusion module (UAF) balances the different feature information by assigning weights to different layers. Finally, a location refinement module (LRM) is constructed to make DMNet pay attention to the boundary details. We compared DMNet with other classical object-detection models on the COD10K dataset. Experimental results indicated that DMNet outperformed others, achieving optimal effects across six evaluation metrics and significantly enhancing detection accuracy.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Electronics
Electronics Computer Science-Computer Networks and Communications
CiteScore
1.10
自引率
10.30%
发文量
3515
审稿时长
16.71 days
期刊介绍: Electronics (ISSN 2079-9292; CODEN: ELECGJ) is an international, open access journal on the science of electronics and its applications published quarterly online by MDPI.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信