检索结果-内蒙古大学图书馆

Multi-information guided camouflaged object detection

IMAGE AND VISION COMPUTING 2025年 156卷

作者： Shi, Caijuan Zhao, Lin Wang, Rui Zhang, Kun Kong, Fanyue Duan, Changyu North China Univ Sci & Technol Coll Artificial Intelligence Tangshan 063210 Hebei Peoples R China Hebei Key Lab Ind Intelligent Percept Tangshan 063210 Hebei Peoples R China

camouflaged object detection (COD) aims to identify the objects hidden in the background environment. Though more and more COD methods have been proposed in recent years, existing methods still perform poorly for detecting small objects, obscured objects, boundary-rich objects, and multi-objects, mainly because they fail to effectively utilize context information, texture information, and boundary information simultaneously. Therefore, in this paper, we propose a Multi-information Guided camouflaged object detection Network (MIGNet) to fully utilize multi-information containing context information, texture information, and boundary information to boost the performance of camouflaged object detection. Specifically, firstly, we design the texture and boundary label and the Texture and Boundary Enhanced Module (TBEM) to obtain differentiated texture information and boundary information. Next, the Neighbor Context Information Exploration Module (NCIEM) is designed to obtain rich multi-scale context information. Then, the Parallel Group Bootstrap Module (PGBM) is designed to maximize the effective aggregation of context information, texture information and boundary information. Finally, Information Enhanced Decoder (IED) is designed to effectively enhance the interaction of neighboring layer features and suppress the background noise for good detection results. Extensive quantitative and qualitative experiments are conducted on four widely used datasets. The experimental results indicate that our proposed MIGNet with good performance of camouflaged object detection outperforms the other 22 COD models.

关键词： camouflaged object detection Multi-information Texture and boundary label Parallel strategy Multi-grouping scales

来源：评论

学校读者我要写书评

暂无评论

EPFDNet: camouflaged object detection with edge perception infrequency domain

引用

IMAGE AND VISION COMPUTING 2025年 154卷

作者： Fang, Xian Chen, Jiatong Wang, Yaming Jiang, Mingfeng Ma, Jianhua Wang, Xin Zhejiang Sci Tech Univ Sch Comp Sci & Technol Hangzhou 310018 Peoples R China Lishui Univ Key Lab Digital Design & Intelligent Manufacture C Lishui 323000 Peoples R China

camouflaged object detection (COD) is a relatively new field of computer vision research. The challenge of this task lies in accurately segmenting camouflaged objects from backgrounds that are similar in appearance. In fact, the generation of reliable edges is an effective mean of distinguishing between the foreground and background of the image, which is beneficial for assisting in determining the location of camouflaged objects. Inspired by this, we design an Edge Encoder that decomposes features into different frequency bands adopting learnable wavelets and focuses on high-frequency components with sufficient edge details to extract accurate edges. Subsequently, the Feature Aggregation Module is proposed to integrate contextual features, which generates rough edge details by sensing the difference between two branch features and use this information to further refine our edge features. Furthermore, the Stage Enhancement Module is developed to enhance the features through reverse attention guidance and dilate convolution, which mines the detailed structural information of the camouflaged objects area by eliminating foreground. The superiority of our proposed method (EPFDNet) over the existing 17 state-of-the-art methods is demonstrated through extensive experiments on three widely used COD benchmark datasets. The code has been released at https://***/LitterMa-820/EPFDNet.

关键词： camouflaged object detection Edge perception Frequency components Reverse attention

来源：评论

学校读者我要写书评

暂无评论

Boundary-guided multi-scale refinement network for camouflaged object detection

引用

VISUAL COMPUTER 2025年第8期41卷 6271-6297页

作者： Ye, Qian Li, Qingwu Huo, Guanying Liu, Yan Zhou, Yan Hohai Univ Coll Informat Sci & Engn Changzhou 213200 Peoples R China Hohai Univ Jiangsu Key Lab Power Transmiss & Distribut Equipm Changzhou 213200 Peoples R China

camouflaged object detection (COD) is significantly more challenging than traditional salient object detection (SOD) due to the high intrinsic similarity between camouflaged objects and their backgrounds, as well as complex environmental conditions. Although current deep learning methods have achieved remarkable performance across various scenarios, they still face limitations in challenging situations, such as occluded targets or scenes with multiple targets. Inspired by the human visual process of detecting camouflaged objects, we introduce BGMR-Net, a boundary-guided multi-scale refinement network designed to identify camouflaged objects accurately. Specifically, we propose the Global Information Extraction (GIE) module to expand the receptive field while preserving detailed cues. Additionally, we design the Boundary-Aware (BA) module, which integrates features across all scales and explores local information from neighboring layer features. Finally, we propose the Multi-information Fusion Dual Stream (MFDS) module, which combines various types of guidance information (i.e., side-output backbone guidance, boundary guidance, neighbor guidance, and global guidance) to generate more fine-grained results through a step-by-step refinement process. Extensive experiments on three benchmark datasets demonstrate that our method significantly outperforms 30 competing approaches. Our code is available at https://***/yeqian1961/BGMR-Net.

关键词： camouflaged object detection Multi-scale feature extraction Boundary-aware learning Convolutional neural network Multi-guidance

来源：评论

学校读者我要写书评

暂无评论

Multidimensional fusion of frequency and spatial domain information for enhanced camouflaged object detection

引用

INFORMATION FUSION 2025年 117卷

作者： Wang, Tingran Yu, Zaiyang Fang, Jianwei Xie, Jinlong Yang, Feng Zhang, Huang Zhang, Liping Du, Minghua Li, Lusi Ning, Xin China Univ Min & Technol Beijing Sch Artificial Intelligence Beijing 100083 Peoples R China Chinese Acad Sci Inst Semicond AnnLab Beijing 100085 Peoples R China China Unicom Software Res Inst Beijing 100048 Peoples R China Univ Chinese Acad Sci Coll Mat Sci & Optoelect Technol Beijing 100049 Peoples R China Chinese Peoples Liberat Army Gen Hosp Med Ctr 1 Dept Emergency Beijing 100853 Peoples R China Old Dominion Univ Dept Comp Sci Norfolk VA 23529 USA

camouflaged object detection (COD) remains a challenging task in computer vision due to the difficulty of distinguishing highly similar targets from complex backgrounds. Existing COD methods often struggle with scene understanding and information utilization, resulting in insufficient accuracy, leading to issues such as background misactivations, target localization losses, and edge blurring. To address these challenges, we propose a novel approach called the Mask and Attention Modulated Information Focusing Network (MAMIFNet), designed to improve COD in the spatial-frequency fusion domain. MAMIFNet introduces a Mask and Attention Modulated Fast Fourier Convolution (MAM-FFC) operator, which adaptively enhances global and local information across spatial and frequency domains through cross-domain masking and attention mechanisms. This operator enables amore comprehensive scene understanding, reducing regional errors such as wide-range false activations and target area losses. To further optimize scene information utilization, the Critical Cue Perception Module (CCPM) is introduced and built upon the MAM-FFC operator. The CCPM refines target foreground focus and foreground-background contrast, mining discriminative cues to improve target localization and edge detection accuracy. Experimental evaluations on four benchmark datasets demonstrate the competitive performance of the proposed method, validating its effectiveness in COD. The code is available at the link below https://***/CHANTILLY2023/MAMIFNet.

关键词： camouflaged object detection Spatial-frequency fusion domain Fast Fourier Convolution

来源：评论

学校读者我要写书评

暂无评论

A three-stage model for camouflaged object detection

引用

NEUROCOMPUTING 2025年 614卷

作者： Chen, Tianyou Ruan, Hui Wang, Shaojie Xiao, Jin Hu, Xiaoguang Chinese Aeronaut Radio Elect Res Inst Shanghai 200241 Peoples R China Minist Ind & Informat Technol Elect Res Inst 5 Guangzhou 511370 Peoples R China Beihang Univ Beijing 100191 Peoples R China

camouflaged objects are typically assimilated into their backgrounds and exhibit fuzzy boundaries. The complex environmental conditions and the high intrinsic similarity between camouflaged targets and their surroundings pose significant challenges inaccurately locating and segmenting these objects in their entirety. While existing methods have demonstrated remarkable performance in various real-world scenarios, they still face limitations when confronted with difficult cases, such as small targets, thin structures, and indistinct boundaries. Drawing inspiration from human visual perception when observing images containing camouflaged objects, we propose a three-stage model that enables coarse-to-fine segmentation in a single iteration. Specifically, our model employs three decoders to sequentially process subsampled features, cropped features, and high-resolution original features. This proposed approach not only reduces computational overhead but also mitigates interference caused by background noise. Furthermore, considering the significance of multi- scale information, we have designed a multi-scale feature enhancement module that enlarges the receptive field while preserving detailed structural cues. Additionally, a boundary enhancement module has been developed to enhance performance by leveraging boundary information. Subsequently, a mask-guided fusion module is proposed to generate fine-grained results by integrating coarse prediction maps with high-resolution feature maps. Our network shows superior performance without introducing unnecessary complexities. Upon acceptance of the paper, the source code will be made publicly available at https://***/clelouch/TSNet.

关键词： camouflaged object detection Coarse-to-fine refinement Convolutional neural network Multi-stage detection

来源：评论

学校读者我要写书评

暂无评论

FLRNet: A bio-inspired three-stage network for camouflaged object detection via filtering, localization and refinement

引用

NEUROCOMPUTING 2025年 626卷

作者： Zhao, Yilin Zhang, Qing Li, Yuetong Shanghai Inst Technol Sch Comp Sci & Informat Engn Shanghai 201418 Peoples R China

camouflaged object detection (COD) aims to segment camouflaged objects, which poses amore challenging task than generic object detection due to the high intrinsic similarity between the foreground and background. In this paper, we propose a bio-inspired three-stage network to uniformly highlight the complete camouflaged objects with explicit boundaries by information filtering, global localization, and progressive refinement. Specifically, we propose the local filtering module (LFM) to mimic the filtering stage by eliminating redundant information using cross-level information to reduce background interference. Furthermore, we design a global localization module (GLM) to determine positions of potential camouflaged objects by directly and progressively aggregating filtered features across different levels. Finally, to fully capture discriminative subtle features, we employ the progressive refinement module (PRM) to distinguish the details and structures by adopting a dual-attention strategy, progressively correcting prediction errors. Quantitative and qualitative experimental results demonstrate that our proposed FLRNet outperforms the state-of-the-art COD methods.

关键词： camouflaged object detection Cross-level feature fusion Information filtering Localization

来源：评论

学校读者我要写书评

暂无评论

Contextual feature fusion and refinement network for camouflaged object detection

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2025年第3期16卷 1489-1505页

作者： Yang, Jinyu Shi, Yanjiao Jiang, Ying Lu, Zixuan Yi, Yugen Shanghai Inst Technol Sch Comp Sci & Informat Engn Shanghai 201418 Peoples R China Jiangxi Normal Univ Sch Software Nanchang 330022 Peoples R China

camouflaged object detection (COD) is a challenging task due to its irregular shape and color similarity or even blending into the surrounding environment. It is difficult to achieve satisfactory results by directly using salient object detection methods due to the low contrast with the surrounding environment and obscure object boundary in camouflaged object detection. To determine the location of the camouflaged objects and achieve accurate segmentation, the interaction between features is essential. Similarly, an effective feature aggregation method is also very important. In this paper, we propose a contextual fusion and feature refinement network (CFNet). Specifically, we propose a multiple-receptive-fields-based feature extraction module (MFM) that obtains features from multiple scales of receptive fields. Then, the features are input to an attention-based information interaction module (AIM), which establishes the information flow between adjacent layers through an attention mechanism. Finally, the features are fused and optimized layer by layer using a feature fusion module (FFM). We validate the proposed CFNet as an effective COD model on four benchmark datasets, and the generalization ability of our proposed model is verified in the salient object detection task.

关键词： Deep learning camouflaged object detection Multiple receptive fields Information exchange

来源：评论

学校读者我要写书评

暂无评论

Seamless detection: Unifying Salient object detection and camouflaged object detection

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 274卷

作者： Liu, Yi Li, Chengxin Dong, Xiaohui Li, Lei Zhang, Dingwen Xu, Shoukun Han, Jungong Changzhou Univ Sch Comp Sci & Artificial Intelligence Changzhou 213159 Peoples R China Sci & Technol Complex Syst Control & Intelligent A Beijing Peoples R China Northwestern Polytech Univ Sch Automat Xian 710129 Peoples R China Tsinghua Univ Dept Automat Beijing 100084 Peoples R China

Achieving joint learning of Salient object detection (SOD) and camouflaged object detection (COD) is extremely challenging due to their distinct object characteristics, i.e., saliency and camouflage. The only preliminary research treats them as two contradictory tasks, training models on large-scale labelled data alternately for each task and assessing them independently. However, such task-specific mechanisms fail to meet real-world demands for addressing unknown tasks effectively. To address this issue, in this paper, we pioneer a task-agnostic framework to unify SOD and COD. To this end, inspired by the agreeable nature of binary segmentation for SOD and COD, we propose a Contrastive Distillation Paradigm (CDP) to distil the foreground from the background, facilitating the identification of salient and camouflaged objects amidst their surroundings. To probe into the contribution of our CDP, we design a simple yet effective contextual decoder involving the interval-layer and global context, which achieves an inference speed of 67 fps. Besides the supervised setting, our CDP can be seamlessly integrated into unsupervised settings, eliminating the reliance on extensive human annotations. Experiments on public SOD and COD datasets demonstrate the superiority of our proposed framework in both supervised and unsupervised settings, compared with existing state-of-the-art approaches. Code is available on https://***/liuyi1989/Seamless-detection.

关键词： Salient object detection camouflaged object detection Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

CSFIN: A lightweight network for camouflaged object detection via cross-stage feature interaction

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 269卷

作者： Li, Minghong Zhao, Yuqian Zhang, Fan Gui, Gui Luo, Biao Yang, Chunhua Gui, Weihua Chang, Kan Cent South Univ Sch Automat Changsha 410083 Hunan Peoples R China Cent South Univ Key Lab Ind Intelligence & Syst Minist Educ Changsha 410083 Hunan Peoples R China Guangxi Univ Sch Comp & Elect Informat Nanning 530004 Guangxi Peoples R China Guangxi Univ Guangxi Key Lab Multimedia Commun & Network Techno Nanning 530004 Guangxi Peoples R China

camouflaged object detection (COD) aims to identify the objects that are hidden in their surroundings, which is a very challenging task due to factors like complex contours and high similarity to the background. Existing COD methods often face the issue of neglecting the impact of feature transformation after the backbone, which leads to accuracy constraints in the subsequent decoding step. Additionally, most COD methods typically demand a greater number of parameters and higher computational complexity to achieve notable performance. To tackle the above issues, a lightweight cross-stage feature interaction network (CSFIN) is proposed in this paper. In the CSFIN, a cross-stage feature perception neck (CSFPN) is designed to achieve effective feature transformation, which improves each stage backbone feature with its adjacent stage information, thus obtaining more comprehensive feature representations for the final decoding. In CSFPN, a bi-directional feature interaction module (BFIM) is introduced between two adjacent stage features to deeply aggregate informative camouflaged cues. As the key component of the BFIM, a multi-scale cross-attention modulation block is constructed to fully investigate the multi-scale long-range dependency between two input features, which can effectively incorporate external guidance. Extensive experimental results illustrate that the CSFIN outperforms other COD models with fewer parameters and lower computational complexity.

关键词： Deep learning Convolutional neural network camouflaged object detection Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An edge-aware high-resolution framework for camouflaged object detection

引用

IMAGE AND VISION COMPUTING 2025年 157卷

作者： Ma, Jingyuan Chen, Tianyou Xiao, Jin Hu, Xiaoguang Wang, Yingxun Beihang Univ Beijing 100191 Peoples R China Chinese Aeronaut Radio Elect Res Inst Shanghai 200241 Peoples R China Inst Remote Sensing Satellite Beijing 100094 Peoples R China

camouflaged objects are often seamlessly assimilated into their surroundings and exhibit indistinct boundaries. The complex environmental conditions and the high intrinsic similarity between camouflaged targets and their backgrounds present significant challenges in accurately locating and fully segmenting these objects. Although existing methods have achieved remarkable performance across various real-world scenarios, they still struggle with challenging cases such as small targets, thin structures, and blurred boundaries. To address these issues, we propose a novel edge-aware high-resolution network. Specifically, we design a High-Resolution Feature Enhancement Module to exploit multi-scale features while preserving local details. Furthermore, we introduce an Edge Prediction Module to generate high-quality edge prediction maps. Subsequently, we develop an Attention-Guided Fusion Module to effectively leverage the edge prediction maps. With these key modules, the proposed model achieves real-time performance at 58 FPS and surpasses 21 state-of-the-art algorithms across six standard evaluation metrics. Source code will be publicly available at https://***/clelouch/EHNet.

关键词： Attention-guided fusion camouflaged object detection Edge-aware segmentation Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：