检索结果-内蒙古大学图书馆

EHAN: An explicitly high-order attention network for accurate camouflaged object detection

NEUROCOMPUTING 2025年 624卷

作者： Wu, Qingbo Wu, Guanxing Chen, Shengyong Tianjin Univ Technol Key Lab Comp Vis & Syst Minist Educ Tianjin 300384 Peoples R China Tianjin Univ Technol Engn Res Ctr Learning Based Intelligent Syst Minist Educ Tianjin 300384 Peoples R China Tianjin Univ Technol Sch Comp Sci & Engn Tianjin 300384 Peoples R China

Wild animals often change their appearance such as color and textures to seamlessly blend into the surrounding environments to avoid predators and enemies, which poses extreme challenges to the task of camouflaged object detection (COD). Recently, most COD methods have struggled to improve the detection performance using attention mechanisms to guide deep networks to focus on the subtle differences between camouflaged objects and backgrounds. However, these approaches tend to suffer from the lower orders inattention, which have limited abilities to model the subtle differences, as observed by applying the Taylor expansion to attention mappings. To solve this problem, we propose Explicitly High-order Attention (EHA) based on the tensor decomposition theory to effectively detect hidden objects, especially at edges. Furthermore, we use EHA as a basic block to design anew COD network EHAN, which consists of four modules: Cross-layer High-order Fusion (CHF), High-order Semantic Attention (HSA), High-order Edge Attention (HEA), and High-order Reverse Attention (HRA). Specifically, CHF progressively improves the features of a backbone by merging three of them at adjacent levels at a time. HSA roughly locates the disguised objects using the features of CHF at the three highest levels, whereas HEA integrates the features of CHF at the two lowest levels to predict edges accurately. HRA aims to discover distractions and incorporate the predicted edges for edge refinement. Extensive experiments on four public datasets demonstrate the superiority of our EHAN over state-of-the-art methods in quality and quantity.

关键词： camouflaged object detection High-order attention Attention mechanism Tensor decomposition

来源：评论

学校读者我要写书评

暂无评论

Semantic-aware representations for unsupervised camouflaged object detection

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2025年 107卷

作者： Lu, Zelin Zhao, Xing Xie, Liang Liang, Haoran Liang, Ronghua Zhejiang Univ Technol Coll Comp Sci & Technol 288 Liuhe Rd Hangzhou 310023 Peoples R China

Unsupervised image segmentation algorithms face challenges due to the lack of human annotations. They typically employ representations derived from self-supervised models to generate pseudo-labels for supervising model training. Using this strategy, the model's performance largely depends on the quality of the generated pseudo-labels. In this study, we design an unsupervised framework to perform COD (camouflaged object detection) without the need for generating pseudo-labels. Specifically, we utilize semantic-aware representations, trained in a self-supervised manner on large-scale unlabeled datasets, to guide the training process. These representations not only capturing rich contextual semantic information but also assist in refining the blurred boundaries of camouflaged objects. Furthermore, we design a framework that integrates these semantic- aware representations with task-specific features, enabling the model to perform the UCOD (Unsupervised camouflaged object detection) task with enhanced contextual understanding. Moreover, we introduce an innovative multi-scale token loss function, which maintain the structural integrity of objects at various scales in the model's predictions through mutual supervision between different features and scales. Extensive experimental validation demonstrates that our model significantly enhances the performance of UCOD, closely approaching the capabilities of state-of-the-art weakly-supervised COD models.

关键词： Semantic-aware segmentation Unsupervised object detection camouflaged object detection

来源：评论

学校读者我要写书评

暂无评论

Bilateral decoupling complementarity learning network for camouflaged object detection

引用

KNOWLEDGE-BASED SYSTEMS 2025年 314卷

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

Existing camouflaged object detection methods have made impressive achievements, however, the interference from highly similar backgrounds, as well as the indistinguishable object boundary, still hider the detection accuracy. In this paper, we propose a three-stage bilateral decoupling complementarity learning network (BDCL-Net) to explore how to utilize the specific advantages of multi-level encoded features for achieving high-quality inference. Specifically, all side-output features are decoupled into two branches to generate three complementary features. Different from previous methods that focus on obtaining the camouflaged object and body boundary, our body modeling stage, which includes a global positioning flow (GPF) module and a multi-scale body warping (MBW) module, is deployed to obtain a global contextual feature that provides coarse localization of potential camouflaged objects and a body feature that emphasizes learning the central areas of camouflaged objects. The detail preservation stage is designed to generate a detail feature that pays attention to the regions around the boundary. Consequently, the body prediction can avoid disturbances from the highly similar backgrounds, while the detail prediction can reduce errors caused by imbalanced boundary pixels. The complementary feature integration (CFI) module in the feature aggregation stage is designed to fuse these complementary features in an interactive learning manner. We conduct extensive experiments on four public datasets to demonstrate the effectiveness and superiority of our proposed network. The code is available at http://***/iuueong/BDCLNet.

关键词： camouflaged object detection Decoupling Complementarity learning Feature grouping

来源：评论

学校读者我要写书评

暂无评论

Multi-level cross-knowledge fusion with edge guidance for camouflaged object detection

引用

KNOWLEDGE-BASED SYSTEMS 2025年 311卷

作者： Sun, Wei Wang, Qianzhou Tian, Yulong Yang, Xiaobao Kong, Xianguang Dong, Yizhuo Zhang, Yanning Xian Univ Posts & Telecommun Sch Comp Sci & Technol Xian Peoples R China Northwestern Polytech Univ Sch Comp Sci & Engn Xian Peoples R China Xidian Univ Sch Mechanoelect Engn Xian Peoples R China Natl Engn Lab Integrated Aerosp Ground Ocean Big D Xian Peoples R China

camouflaged object detection aims to identify objects that are "perfectly"assimilated into their surroundings, which has a wide range of valuable applications. The key challenge is that there exists high intrinsic similarities between the candidate objects and noise background. Despite the numerous learning frameworks developed in recent years to address this issue, they still struggle when confronted with highly deceptive camouflaged objects. In response, we propose a coarse-to-fine framework that leverages rough target positioning guided by edge semantics and refined identification assisted by cross-knowledge. Specifically, we dynamically mine additional object-related edge cues to guide representation learning in camouflaged object detection. This process focuses on exploring the initial object structure and facilitating the search for coarse regions of objects across multiple observation dimensions, mirroring biological mechanisms. Subsequently, multi-level cross- knowledge, refined through aggregation, aids in decoding the representation of precise regions. Employing a deep supervision strategy from top to bottom, our framework achieves accurate camouflaged object detection. Experiments conducted on various widely-used benchmark datasets demonstrate that our proposed network outperforms previous methods both qualitatively and quantitatively.

关键词： camouflaged object detection Cross-knowledge fusion Edge guidance

来源：评论

学校读者我要写书评

暂无评论

Certainty-guided Reasoning and Refinement Network for camouflaged object detection

Certainty-guided Reasoning and Refinement Network for Camouf...

引用

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

作者： Lai, Bifan Sun, Meijun Zhao, Junkun Zhou, Yan College of Intelligence and Computing Tianjin University Tianjin China School of Disaster and Emergency Medicine Tianjin University Tianjin China

ISBN: (纸本)9798350368741

camouflaged object detection (COD), which aims to segment objects that are highly similar to their background, is a valuable yet challenging task. Due to the interference of clutter and noise in the background, existing methods often struggle to avoid misleading and accurately segment the camouflaged object. In this paper, we propose a novel Certainty-guided Reasoning and Refinement Network (CRRNet) for COD. The core idea is to first explicitly reason under accurate knowledge of camouflaged objects, and then refine the uncertain regions by a certainty propagation strategy. To achieve this, we innovatively propose two modules: the Certainty-guided Reasoning Module and Uncertain Region Refinement Module. Experimental results prove that the proposed CRRNet outperforms 12 state-of-the-art methods on three COD benchmark datasets. © 2025 IEEE.

关键词： camouflaged object detection certainty-guided reasoning image segmentation

来源：评论

学校读者我要写书评

暂无评论

Rethinking camouflaged object detection via Foreground-Background Interactive Learning

Rethinking Camouflaged Object Detection via Foreground-Backg...

引用

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

作者： Zhang, Chenxi Zhang, Qing Wu, Jiayun Faculty of Intelligence Technology Shanghai Institute of Technology Shanghai China

ISBN: (纸本)9798350368741

camouflaged object detection focuses on the challenge of segmenting objects that visually blend into their background. The effectiveness of camouflage strategies hinges on how well objects interact with their background to minimize their visibility. Based on this insight, we propose a novel Foreground-Background Interactive Learning Network (FBINet), which independently decouples foreground and background information, and facilitates bi-directional interactions. This allows the network to progressively complement each other, leading to high-quality predictions with clear boundaries. To the best of our knowledge, this is the first attempt to tackle the camouflaged object detection task through interactive learning between foreground and background, which not only better reveals camouflage patterns but also offers a new perspective in this field. Experimental results on three datasets demonstrate that our proposed FBINet outperforms current state-of-the-art methods in performance while maintaining a low computational cost, making it applicable for real-world scenarios. The code will be available at https://***/bbdjj/FBINet. © 2025 IEEE.

关键词： camouflaged object detection foreground-background interaction image segmentation

来源：评论

学校读者我要写书评

暂无评论

camouflaged object detection based on context-aware and boundary refinement

引用

APPLIED INTELLIGENCE 2023年第19期53卷 22429-22445页

作者： Shi, Caijuan Ren, Bijuan Chen, Houru Zhao, Lin Lin, Chunyu Zhao, Yao North China Univ Sci & Technol Tangshan 063210 Peoples R China Hebei Key Lab Ind Intelligent Percept Tangshan 063210 Peoples R China Beijing Jiaotong Univ Beijing 100044 Peoples R China

camouflaged object detection (COD) has been increasingly studied and the detection performance has been greatly improved based on deep learning models in recent years. However, the context and boundary information have not been efficiently used simultaneously in the existing COD methods, leading to inferior detection for large camouflaged objects, occluded objects, multiple and small objects, and objects with rich boundaries. Therefore, to effectively enhance the performance of COD, we propose a novel camouflaged object detection model, i.e., context-aware and boundary refinement (CABR). Specifically, CABR mainly consists of three modules: the global context information enhanced module (GCIEM), the attention-inducing neighbor fusion module (AINFM), and the boundary refinement module (BRM). GCIEM is designed to fully capture the long-range dependencies to obtain rich global context information to completely detect large objects and occluded objects. AINFM is capable of adaptively fusing adjacent layers to focus on the global and local context information simultaneously to improve the detection performance of multiple and small camouflaged objects effectively. BRM can refine the boundaries by utilizing the spatial information in low-level features and suppressing the non-camouflage factors to detect camouflaged objects with rich boundaries effectively. Quantitative and qualitative experiments are conducted on four benchmark datasets, and the experimental results demonstrate the effectiveness of our CABR with competitive performance to existing state-of-the-art methods according to most evaluation metrics.

关键词： camouflaged object detection Context information Boundary refinement Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

camouflaged object detection via Context-Aware Cross-Level Fusion

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第10期32卷 6981-6993页

作者： Chen, Geng Liu, Si-Jie Sun, Yu-Jia Ji, Ge-Peng Wu, Ya-Feng Zhou, Tao Northwestern Polytech Univ Xian 710072 Peoples R China Sch Comp Sci & Engn Natl Engn Lab Integrated Aerospace Ground Ocean Xian Peoples R China Sch Power & Energy Data Proc Ctr Xian Peoples R China Inner Mongolia Univ Sch Comp Sci Hohhot 010021 Peoples R China Wuhan Univ Artificial Intelligence Inst Sch Comp Sci Wuhan 430072 Peoples R China Minist Educ Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China

camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., object size and shape. To address these challenges, we propose a novel Context-aware Cross-level Fusion Network ((CF)-F-2-Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, we compute informative attention coefficients from multi-level features with our Attention-induced Cross-level Fusion Module (ACFM), which further integrates the features under the guid ance of attention coefficients. We then propose a Dual-branch Global Context Module (DGCM) to refine the fused features for informative feature representations by exploiting rich global context information. Multiple ACFMs and DGCMs are integrated in a cascaded manner for generating a coarse prediction from high-level features. The coarse prediction acts as an attention map to refine the low-level features before passing them to our Camouflage Inference Module (CIM) to generate the final prediction. We perform extensive experiments on three widely used benchmark datasets and compare (CF)-F-2-Net with state-of the-art (SOTA) models. The results show that (CF)-F-2-Net is an effective COD model and outperforms SOTA models remark ably. Further, an evaluation on polyp segmentation datasets demonstrates the promising potentials of our (CF)-F-2-Net in COD downstream applications. Our code is publicly available at: https://***/Ben57882/C2FNet-TSCVT

关键词： camouflaged object detection context-aware deep learning feature fusion polyp segmentation

来源：评论

学校读者我要写书评

暂无评论

camouflaged object detection with Feature Grafting and Distractor Aware

Camouflaged Object Detection with Feature Grafting and Distr...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Song, Yuxuan Li, Xinyue Qi, Lin Ocean Univ China Coll Comp Sci & Technol Qingdao Peoples R China

ISBN: (纸本)9781665468916

The task of camouflaged object detection (COD) aims to accurately segment camouflaged objects that integrated into the environment, which is more challenging than ordinary detection as the texture between the target and background is visually indistinguishable. In this paper, we proposed a novel Feature Grafting and Distractor Aware network (FDNet) to handle the COD task. Specifically, we use CNN and Transformer to encode multi-scale images in parallel. In order to better explore the advantages of the two encoders, we design a cross-attentionbased Feature Grafting Module to graft features extracted from Transformer branch into CNN branch, after which the features are aggregated in the Feature Fusion Module. A Distractor Aware Module is designed to explicitly model the two possible distractor in the COD task to refine the coarse camouflage map. We also proposed the largest artificial camouflaged object dataset which contains 2000 images with annotations, named ACOD2K. We conducted extensive experiments on four widely used benchmark datasets and the ACOD2K dataset. The results show that our method significantly outperforms other state-of-the-art methods. The code and the ACOD2K will be available at https://***/syxvision/FDNet.

关键词： camouflaged object detection Transformer Convolutional Neural Networks Distractor

来源：评论

学校读者我要写书评

暂无评论

camouflaged object detection VIA STYLE TRANSFER-BASED DATA AUGMENTATION 31

CAMOUFLAGED OBJECT DETECTION VIA STYLE TRANSFER-BASED DATA A...

引用

2024 International Conference on Image Processing

作者： Lu, Dongni Chen, Jiaxuan Chen, Haiyan Peng, Ziyi Quan, Rong Qin, Jie Nanjing Univ Aeronaut & Astronaut Nanjing Peoples R China

ISBN: (纸本)9798350349405;9798350349399

Infrared (IR) images can be seen as complementary to visible light (RGB) images, as they can capture accurate targets in low-visibility conditions. However, camouflaged object detection (COD) based on RGB and IR images is expensive. To this end, we propose to exploit a style transfer-based data augmentation method to generate pseudo-IR images by absorbing the style information of IR images into RGB images, and to perform COD based on RGB and the pseudo-IR images. For RGB and IR-based COD, we propose a novel Edge-guided Uncertainty-aware Fusion Network (EUFNet), to make better use of the complementarity between the two kinds of images. Specifically, an uncertainty-aware fusion module is first proposed to aggregate RGB and IR features by estimating their uncertainties. Then, an edge enhancement module is proposed to extract and enhance the edge information in multiple stages. Lastly, a hierarchical integration module is designed to integrate RGB and IR features with edge cues. Extensive experiments demonstrate the effectiveness of the generated pseudo-IR images as well as the proposed EUFNet. The code is available at https://***/csdahunzi/COD.

关键词： camouflaged object detection data augmentation style transfer

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：