检索结果-内蒙古大学图书馆

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Yin, Pengyu Fu, Keren Zhao, Qijun Sichuan Univ Coll Comp Sci Chengdu Peoples R China Sichuan Univ Natl Key Lab Fundamental Sci Synthet Vis Chengdu Peoples R China

ISBN: (纸本)9789819788576;9789819788583

Visual salient object detection (SOD) aims to discover eye-catching salient objects, while camouflaged object detection (COD) seeks to segment objects that are visually hidden in their surrounding environment. In this paper, considering the difficulty in defining salient and camouflaged properties of data when large-scale automated processing is launched, we propose a novel key object detection (KOD) task, which attempts to unify SOD and COD into one single task. This task treats both salient and camouflaged objects as key objects and aims to detect such key objects with salient and camouflaged properties. For KOD, we design a dual-branch network called DVNet, with a segmentation branch detecting key objects with salient and camouflaged properties in the scene, and additionally a judgment branch showcasing their saliency/camouflage degrees. Moreover, DVNet introduces a feature purification module (FPM) to focus more intently on mining features of key objects and employs a round-robin training strategy to enhance learning consistency. To demonstrate the effectiveness of DVNet for the KOD task, we construct a benchmark test set named KOD10K. We conduct extensive experiments on KOD10K and public SOD and COD datasets. DVNet achieves the best performance on KOD10K and also achieves decent performance on both SOD and COD datasets, demonstrating the significance of the proposed KOD task and the superiority of DVNet in detecting salient and camouflaged objects simultaneously.

关键词： Key object detection Salient object detection camouflaged object detection Feature purification module

来源：评论

学校读者我要写书评

暂无评论

CAMFNet: complex camouflaged object detection via context-aware and adaptive multilevel feature fusion network

引用

VISUAL COMPUTER 2025年 1-16页

作者： Zhou, Bingqin Li, Xionglong Li, Miaoqing Yang, Kun Li, Wenyang Xu, Jing Hangzhou Dianzi Univ Sch Comp Sci & Technol Hangzhou 310018 Peoples R China Hangzhou Dianzi Univ Sch Mat & Environm Engn Hangzhou 310018 Peoples R China Key Lab Brain Machine Collaborat Intelligence Zhej Hangzhou 310018 Peoples R China Zhejiang Gongshang Univ Sch Stat & Math Hangzhou 310018 Peoples R China

camouflaged object detection (COD) aims to identify and segment camouflaged objects hidden in the environment. Previous methods based on CNN and Transformer still struggle to cope with more challenging scenes such as occlusions, rich edge detail and multiple objects. The performance of existing COD methods needs to be further improved. To address this issue, we have proposed a novel three-stage method, CAMFNet, for camouflaged object detection. The method uses PVTv2 as a backbone network and consists of three newly designed modules: (1) A multi-scale contextual feature enhancement (MCFE) module is designed to optimize the candidate features extracted by the Pvtv2 backbone network;(2) a multilevel interaction (MID) module is designed to generate coarse location information from the optimized candidate features;and (3) an adaptive feature fusion (AFF) module is designed to adaptively fuse the features from the encoder and decoder and achieve more accurate detection by using the position information provided by the MID. Ablation experiments show that the proposed three key modules are effective in improving the overall performance. Extensive experimental results on four benchmark COD datasets show that the CAMFNet outperforms 22 competitive methods. Our code is publicly available at https://***/Dp-zhou/CAMFNet.

关键词： Convolutional neural network camouflaged object detection Multi-scale contextual feature enhancement Edge-based adaptive feature fusion

来源：评论

学校读者我要写书评

暂无评论

Attention and Boundary Induced Feature Refinement Network for camouflaged object detection 7th

Attention and Boundary Induced Feature Refinement Network fo...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Zhong, Junmin Wang, Anzhi Guizhou Normal Univ Sch Big Data & Comp Sci Guiyang 550025 Peoples R China

ISBN: (纸本)9789819786848;9789819786855

The intrinsic similarity between camouflaged objects and background environment makes camouflaged object detection (COD) task more challenging than traditional object detection task. Since the boundary of the camouflage object is difficult to determine, the existing COD method often cannot accurately identify the boundary details and complete structure of camouflage object. To solve these challenges, we propose a novel attention and boundary guided feature refinement network (ABNet) for improving the performance of COD. Specifically, ABNet mainly includes three main modules: multi-resolution feature enhancement module (MFEM), attention-induced edge-aware module (AIEM), and boundary-guide feature interaction module (BFIM). The MFEM is introduced to enhance the single-layer feature and maintain high-quality detailed information. Additionally, the AIEM is designed to model edge features effectively from the enhanced feature. Finally, the BFIM is incorporated to focus on the structural details of camouflaged objects, which aims to explore multi-level features between global and local contextual information simultaneously for facilitating more complete detection. Extensive experiments have proved the effectiveness of the proposed model, and our model demonstrates competitive performance compared to existing state-of-the-art models on four benchmark datasets.

关键词： camouflaged object detection Attention mechanism Boundary cues

来源：评论

学校读者我要写书评

暂无评论

ECLNet: A Compact Encoder-Decoder Network for Efficient camouflaged object detection 7th

ECLNet: A Compact Encoder-Decoder Network for Efficient Camo...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Yang, Longwu Chen, Haiyan Lu, Dongni Qin, Jie Nanjing Univ Aeronaut & Astronaut Nanjing 210016 Peoples R China

ISBN: (纸本)9789819784929;9789819784936

camouflaged object detection (COD) is a valuable yet challenging task due to the resemblance between target objects and their surroundings. Existing methods have made impressive progress on COD by focusing on accurate segmentation of regions and boundaries. However, they still suffer from two major limitations: (1) lack of trade-offs between model accuracy and efficiency. (2) ignorance of the correlation between localization and edge cues. To tackle these issues, we propose a novel Edge-localization Cooperative Learning Network (ECLNet), which employs a compact encoder-decoder framework to effectively exploit the interaction between localization and edge cues. Through cooperative learning and compact structure design, ECLNet is enabled to extract comprehensive features with less computational costs, thus achieving a satisfactory trade-off between model accuracy and efficiency. Specifically, we propose an Edge-localization Interaction Module (EIM), which employs cooperative learning to simultaneously obtain edge details and enhanced localization perception. Moreover, we design a Hierarchical Feature Fusion Module (HFFM) to further fuse extracted features under the guidance of localization and edge cues. Extensive experiments on three challenging COD benchmarks demonstrate that ECLNet achieves more efficient performance compared to 14 state-of-the-art methods, improving 18.2% and 3% in terms of FPS and F-beta(omega) on COD10K.

关键词： camouflaged object detection Efficient Network Cooperative Learning

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised camouflaged object detection: Multi Information Fusion Combined with Adaptive Receptive Field Selection Network 7th

Semi-Supervised Camouflaged Object Detection: Multi Informat...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Yang, Guang Xiao, Feng Liu, Ruyu Zhang, Jiawei Zhang, Jianhua Chen, Shengyong Tianjin Univ Technol Tianjin 300380 Peoples R China Hangzhou Normal Univ Hangzhou 311121 Peoples R China

ISBN: (纸本)9789819788576;9789819788583

camouflaged object detection is focused on segmenting objects concealed within their surroundings. This technology can be applied in various fields such as medical image analysis, wildlife conservation, autonomous driving, and others. Existing semi-supervised camouflage object detection methods often suffer from poor network performance due to the accumulation of incorrect pseudo labels, and they fail to fully utilize multi-scale features or account for the diverse scale contexts necessary for various sizes of camouflage objects. In this paper, we propose an innovative semi-supervised learning strategy. We employ a dual-branch network named CAMNet, utilizing salient maps corresponding to camouflage objects to aid detection. We also introduce a Multi-Information Fusion Feature Perception module (MIF) and an Adaptive Receptive Field Selection module (ARFS), which are integrated into the network. Ultimately, we perform thorough comparative experiments on the R2C7K, COD-Water, and COD-Jungle datasets, showcasing superior performance in contrast to current state-of-the-art methods. We also conduct ablation experiments, further confirming the effectiveness of the proposed modules.

关键词： camouflaged object detection Semi-supervised learning Computer vision Deep learning

来源：评论

学校读者我要写书评

暂无评论

camouflaged object detection with CNN-Transformer Harmonization and Calibration

Camouflaged Object Detection with CNN-Transformer Harmonizat...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhao, Yilin Zhang, Qing Li, Yuetong College of Information Engineering Shanghai Institute of Technology Shanghai China

ISBN: (纸本)9798350368741

camouflaged object detection (COD) aims to segment objects that visually blend into their surroundings. However, the subtle differences between camouflaged objects and the background make this task highly challenging. Therefore, how to represent and learn local details and global contexts is crucial for improving detection performance. In this paper, we propose a novel COD network which synergistically leverages the distinct but complementary local and global knowledge to capture the camouflaged objects and identify imperceptible boundaries. Specifically, we design a Feature Coherence Harmonization module to integrate intra-layer features by bridging the knowledge gap between convolutional neural network (CNN) features, which focus on local patterns, and Transformer features, which capture global relationships. Furthermore, we propose a Cross-layer Feature Calibration Module that adaptively aligns inter-layer features, progressively aggregating diverse information to achieve an accurate prediction. Experimental results on COD benchmark datasets demonstrate that the proposed network significantly outperforms state-of-the-art approaches. © 2025 IEEE.

关键词： camouflaged object detection inter-layer aggregation intra-layer integration

来源：评论

学校读者我要写书评

暂无评论

camouflaged object detection via Neural Architecture Search

Camouflaged Object Detection via Neural Architecture Search

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Xin Fu, Keren Zhao, Qijun College of Computer Science Sichuan University Chengdu China

ISBN: (纸本)9798350368741

The core challenge in camouflaged object detection (COD) is identifying objects that blend seamlessly with their surroundings. Existing methods emulate the strategies biological organisms break camouflage by manually constructing modules with expert knowledge from existing segmentation tasks, making it difficult to accurately understand complex and unique camouflage semantics. We are the first to apply neural architecture search (NAS) to COD, introducing an automatic localization and refinement network called ALRNet. It explores a large search space to discover more effective camouflage-specific modules. Specifically, we propose a search-based automatic receptive field block (ARFB) to adaptively excavate hierarchical discriminative cues and decouple features in a multi-branch architecture. Moreover, we introduce an edge-assisted explicit and implicit refinement (EEIR) module, combining explicit priors with implicit search to create a dual-task structure for edge and segmentation knowledge interaction. Experiments on four benchmarks demonstrate that ALRNet outperforms 15 state-of-the-art methods. Codes are available at https://***/BoydeLi/ALRNet. © 2025 IEEE.

关键词： camouflaged object detection dual-task learning edge prediction neural architecture search

来源：评论

学校读者我要写书评

暂无评论

Stealth sight: A multi perspective approach for camouflaged object detection

引用

IMAGE AND VISION COMPUTING 2025年 157卷

作者： Domnic, S. Jayanthan, K. S. Natl Inst Technol Tiruchirappalli Tamil Nadu India

camouflaged object detection (COD) is a challenging task due to the inherent similarity between objects and their surroundings. This paper introduces Stealth Sight, a novel framework integrating multi-view feature fusion and depth-based refinement to enhance segmentation accuracy. Our approach incorporates a pretrained multi-view CLIP encoder and a depth extraction network, facilitating robust feature representation. Additionally, we introduce a cross-attention transformer decoder and a post-training pruning mechanism to improve efficiency. Extensive evaluations on benchmark datasets demonstrate that Stealth Sight outperforms state-of-the-art methods in camouflaged object segmentation. Our method significantly enhances detection in complex environments, making it applicable to medical imaging, security, and wildlife monitoring.

关键词： camouflaged object detection Transformer Pretrained models Multi-view Depth-view Pruning After Training(PAT) Fine-grained segmentation Resource-constrained environments

来源：评论

学校读者我要写书评

暂无评论

When super-resolution meets camouflaged object detection: A comparison study

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2025年 253卷

作者： Wen, Juan Cheng, Shupeng Hou, Weiyan Van Gool, Luc Timofte, Radu Zhengzhou Univ Sch Informat Engn Zhengzhou 450001 Peoples R China Swiss Fed Inst Technol Comp Vis Lab D ITET CH-8092 Zurich Switzerland Univ Southern Calif Viterbi Sch Engn Los Angeles CA 90089 USA Sofia Univ KU Leuven Proc Speech & Images PSI B-3000 Leuven Belgium Sofia Univ INSAIT Sofia 1784 Bulgaria Univ Wurzburg Comp Vis Lab CAIDAS & IFI D-97070 Wurzburg Germany

Super-resolution (SR) and camouflage object detection (COD) are two prominent topics in the field of computer vision, with various joint applications. However, in previous work, these two areas were often studied in isolation. In this paper, we conduct a comprehensive comparative evaluation of both for the first time. Specifically, we benchmark different super-resolution methods on commonly used COD datasets while also evaluating the robustness of different COD models using COD data processed by SR methods. Experiments reveal challenges in preserving semantic information due to differences in targets and features between the two domains. COD relies on extracting semantic information from low-resolution images to identify camouflage targets. There is a risk of losing or distorting important semantic details during the application of SR techniques. Balancing the enhancement of spatial resolution with the preservation of semantic information is crucial for maintaining the accuracy of COD algorithms. Therefore, we propose a new SR model called Dilated Super- resolution (DISR) to enhance SR performance on COD, achieving state-of-the-art results on five commonly used SR datasets. The Urban100 x4 dataset task improved by 0.38 dB. Using low-resolution images processed by DISR for COD tasks can enhance target visibility and significantly improve the performance of COD tasks. Our goal is to leverage the synergies between these two domains, draw insights from the complementarity of techniques in both fields, and provide insights and inspiration for future research in both communities.

关键词： Super-resolution camouflaged object detection Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing camouflaged object detection through contrastive learning and data augmentation techniques

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 141卷

作者： Guo, Cunhan Huang, Heyan Univ Chinese Acad Sci Sch Emergency Management Sci & Engn 1 Yanqihu East Rd Beijing 101400 Peoples R China Beijing Inst Technol Southeast Acad Informat Technol 1998 Licheng Middle Ave Putian 351100 Fujian Peoples R China Beijing Inst Technol Sch Comp Sci & Technol 5 Zhongguancun South St Beijing 101400 Peoples R China

camouflaged object detection (COD) aims to locate and segment objects that blend into their surroundings, presenting significant challenges due to the high similarity between the objects and their background. This work introduces a novel approach, Contrastive Learning with Augmented Data (CLAD), which enhances COD performance by leveraging contrastive learning and data augmentation. Our method formulates a simplified task by placing camouflaged objects in new environments, creating positive and negative samples for contrast learning. This process strengthens the model's ability to differentiate camouflaged objects from complex backgrounds. Furthermore, we introduce a concatenated feature enhancement module to integrate and enrich multi-scale features, improving the overall expressive power of the model. Extensive experiments on four benchmark datasets demonstrate that CLAD outperforms state-of-the-art COD methods, and its effectiveness extends to salient object detection tasks, achieving competitive results across multiple metrics.

关键词： camouflaged object detection Contrastive learning Data augmentation Deep learning Computer vision

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：