检索结果-内蒙古大学图书馆

Feature-aware and iterative refinement network for camouflaged object detection

VISUAL COMPUTER 2024年第7期41卷 4741-4758页

作者： Ge, Yanliang Ren, Junchao Zhang, Cong He, Min Bi, Hongbo Zhang, Qiao Northeast Petr Univ Sch Elect Informat Engn Daqing 163000 Peoples R China China Mobile Commun Grp Heilongjiang Co Ltd Daqing Branch Daqing 163000 Peoples R China China Univ Petr East China Sch Comp Sci & Technol Qingdao 266580 Peoples R China

camouflaged object detection (COD) is engineered to identify objects using visual camouflage techniques that seamlessly blend with the background. Although the existing methods have achieved good performance, it is still difficult to detect camouflaged objects that are extremely similar to the background. In this paper, we propose a new feature-aware and iterative refinement network (FIRNet) for exploring the integrity of hidden objects. Specifically, we design a multivariate feature perception module to capture multivariate context features better to locate the original region of the camouflaged object. Furthermore, we propose an iterative refinement module to investigate the correlation among distinct features, facilitating the iterative refinement of camouflaged objects. Rigorous experimentation across four challenging benchmark datasets demonstrates that FIRNet overcomes performance bottlenecks in different scenarios, yielding notable results in comparison with 21 state-of-the-art methods. It is worth noting that FIRNet achieves a score of 0.927 on the F beta max\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_{\beta }<^>\mathrm{{max}}$$\end{document} on the dataset COD10K, which is 1.0% higher than that of the suboptimal FPNet method. Concurrently, we examined the significance of FIRNet on two additional COD datasets, showcasing its adaptability for diverse downstream applications. The code and results of our method are available at https://***/RJC0608/FIRNet.

关键词： camouflaged object detection Deep learning Multivariate feature perception Iterative refinement

来源：评论

学校读者我要写书评

暂无评论

Ternary symmetric fusion network for camouflaged object detection

引用

APPLIED INTELLIGENCE 2023年第21期53卷 25216-25231页

作者： Deng, Yangyang Ma, Jianxin Li, Yajun Zhang, Min Wang, Li Henan Univ Sch Artificial Intelligence Zhengzhou 450046 Peoples R China Henan Univ Eurasia Int Sch Kaifeng 475001 Peoples R China

Camouflage object detection (COD) is designed to locate objects that are "seamlessly" embedded in the surrounding environment. camouflaged object detection is a challenging task due to the high intrinsic similarities between objects and their backgrounds, as well as the low boundary contrast between them. To address this problem, this paper proposes a new ternary symmetric fusion network (TSFNet), which can detect camouflaged objects by fully fusing features of different levels and scales. Specifically, the network proposed in this paper mainly contains two key modules: the location-attention search (LAS) module and the ternary symmetric interaction fusion (TSIF) module. The location-attention search module makes full use of contextual information to position potential target objects from a global perspective while enhancing feature representation and guiding feature fusion. The ternary symmetric interaction fusion module consists of three branches: bilateral branches gather rich contextual information of multi-level features, and a middle branch provides fusion attention coefficients for the other two branches. The strategy can effectively achieve information fusion between low- and high-level features, and then achieve the refinement of edge details. Experimental results show that the method is an effective COD model and outperforms existing models. Compared with the existing model SINetV2, TSFNet significantly improves the performance by 3.5% weighted F-measure and 8.1% MAE on the COD10K.

关键词： camouflaged object detection Deep learning Receptive field Context information

来源：评论

学校读者我要写书评

暂无评论

MSCAF-Net: A General Framework for camouflaged object detection via Learning Multi-Scale Context-Aware Features

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第9期33卷 4934-4947页

作者： Liu, Yu Li, Haihang Cheng, Juan Chen, Xun Hefei Univ Technol Dept Biomed Engn Hefei 230009 Peoples R China Hefei Univ Technol Anhui Prov Key Lab Measuring Theory & Precis Instr Hefei 230009 Peoples R China Univ Sci & Technol China Dept Elect Engn & Informat Sci Hefei 230026 Peoples R China

The aim of camouflaged object detection (COD) is to find objects that are hidden in their surrounding environment. Due to the factors like low illumination, occlusion, small size and high similarity to the background, COD is recognized to be a very challenging task. In this paper, we propose a general COD framework, termed as MSCAF-Net, focusing on learning multi-scale context-aware features. To achieve this target, we first adopt the improved Pyramid Vision Transformer (PVTv2) model as the backbone to extract global contextual information at multiple scales. An enhanced receptive field (ERF) module is then designed to refine the features at each scale. Further, a cross-scale feature fusion (CSFF) module is introduced to achieve sufficient interaction of multi-scale information, aiming to enrich the scale diversity of extracted features. In addition, inspired the mechanism of the human visual system, a dense interactive decoder (DID) module is devised to output a rough localization map, which is used to modulate the fused features obtained in the CSFF module for more accurate detection. The effectiveness of our MSCAF-Net is validated on four benchmark datasets. The results show that the proposed method significantly outperforms state-of-the-art (SOTA) COD models by a large margin. Besides, we also investigate the potential of our MSCAF-Net on some other vision tasks that are highly related to COD, such as polyp segmentation, COVID-19 lung infection segmentation, transparent object detection and defect detection. Experimental results demonstrate the high versatility of the proposed MSCAF-Net. The source code and results of our method are available at https://***/yuliu316316/MSCAF-COD.

关键词： camouflaged object detection contextual infor-mation multi-scale features deep learning polyp segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Texture-Aware Features for camouflaged object detection

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第3期33卷 1157-1167页

作者： Ren, Jingjing Hu, Xiaowei Zhu, Lei Xu, Xuemiao Xu, Yangyang Wang, Weiming Deng, Zijun Heng, Pheng-Ann South China Univ Technol Sch Comp Sci & Engn Guangzhou 510640 Peoples R China Chinese Univ Hong Kong Dept Comp Sci & Engn Hong Kong Peoples R China Hong Kong Univ Sci & Technol Guangzhou Thrust Robot & Autonomous Syst ROAS Guangzhou 511400 Guangdong Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangdong Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou 510640 Peoples R China South China Univ Technol State Key Lab Subtrop Bldg Sci Guangzhou 510640 Peoples R China South China Univ Technol Prov Key Lab Computat Intelligence & Cyberspace In Guangzhou 510640 Peoples R China Hong Kong Metropolitan Univ Sch Sci & Technol Hong Kong Peoples R China

camouflaged object detection is a challenging task that aims to identify objects having similar texture to the surroundings. This paper presents to amplify the subtle texture difference between camouflaged objects and the background for camouflaged object detection by formulating multiple texture-aware refinement modules to learn the texture-aware features in a deep convolutional neural network. The texture-aware refinement module computes the biased co-variance matrices of feature responses to extract the texture information, adopts an affinity loss to learn a set of parameter maps that help to separate the texture between camouflaged objects and the background, and leverages a boundary-consistency loss to explore the structures of object details. We evaluate our network on the benchmark datasets for camouflaged object detection both qualitatively and quantitatively. Experimental results show that our approach outperforms various state-of-the-art methods by a large margin.

关键词： Feature extraction object detection Convolution Covariance matrices Semantics Deep learning Data mining camouflaged object detection deep features texture-aware

来源：评论

学校读者我要写书评

暂无评论

Efficient camouflaged object detection via Progressive Refinement Network

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 231-235页

作者： Zhang, Dongdong Wang, Chunping Fu, Qiang Army Engn Univ PLA Shijiazhuang Campus Shijiazhaung 050003 Peoples R China

camouflaged object detection (COD) aims to identify objects that are perfectly concealed in their surroundings and has attracted increasing attention in recent years. The challenge with COD is the intrinsic similarity between camouflaged objects and background, as well as the weak boundary that often accompanies camouflaged objects. In this letter, a Progressive Refinement Network called PRNet is proposed based on human perception of camouflaged images. Specifically, we develop a position-aware module to roughly locate the position of camouflaged objects by reverse-guiding with high-level semantic information. Moreover, an edge-guided fusion module is designed to simultaneously refine the boundaries and regions of camouflaged objects by using edge features as a guide in cross-level feature fusion. Benefited from the utility of the above two modules, our PRNet is able to identify camouflaged objects accurately and quickly. Numerous experiments on four widely used benchmark datasets demonstrate that the proposed PRNet is an efficient COD model, outperforming 14 state-of-the-art algorithms significantly and running at a real-time speed (41.0 FPS).

关键词： Image edge detection Feature extraction Computer vision Semantics object detection Visualization Training camouflaged object detection position-aware module edge-guided fusion module cross-level feature fusion

来源：评论

学校读者我要写书评

暂无评论

FINet: Frequency Injection Network for Lightweight camouflaged object detection

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 526-530页

作者： Liang, Weiyun Wu, Jiesheng Wu, Yanfeng Mu, Xinyue Xu, Jing Nankai Univ Coll Artificial Intelligence Tianjin 300350 Peoples R China Zhejiang Lab Dept Artificial Intelligence Hangzhou 311121 Peoples R China

Existing camouflaged object detection (COD) methods typically have large model parameters and computations, hindering their deployment in real-world applications. Although using lightweight backbones can help alleviate this problem, their weaker feature representation often leads to performance degradation. To address this issue, we observe that frequency information has shown effective for cumbersome networks, but its effectiveness for lightweight ones has not been thoroughly investigated. Biological studies indicate that the human visual system utilizes distinct neural pathways to respond to different frequency stimuli, contributing to specialization and efficiency. Motivated by this, we propose an efficient frequency injection module (FIM) to aid lightweight backbone features by separately injecting detailed high frequency and object-level low frequency cues at each stage. FIM can be used as a plug-and-play component in existing COD networks to enhance backbone features at a low cost. With FIM, our proposed frequency injection network (FINet) achieves competitive performance against most state-of-the-art methods with much faster speed (692FPS for the input size of 384x384) and fewer parameters (3.74 M).

关键词： Feature extraction Frequency-domain analysis High frequency object detection Decoding Benchmark testing Training camouflaged object detection lightweight model frequency information feature fusion

来源：评论

学校读者我要写书评

暂无评论

Mask-and-Edge Co-Guided Separable Network for camouflaged object detection

引用

IEEE SIGNAL PROCESSING LETTERS 2023年 30卷 748-752页

作者： Wu, Jiesheng Liang, Weiyun Hao, Fangwei Xu, Jing Nankai Univ Coll Artificial Intelligence Tianjin 300350 Peoples R China

camouflaged object detection (COD) involves segmenting objects that share similar patterns, such as color and texture, with their surroundings. Current methods typically employ multiple well-designed modules or rely on edge cues to learn object feature representations for COD. However, these methods still struggle to capture the discriminative semantics between camouflaged objects (foreground) and background, possibly generating blurry prediction maps. To address these limitations, we propose a novel mask-and-edge co-guided separable network (MECS-Net) for COD that leverages both edge and mask cues to learn more discriminative representations and improve detection performance. Specifically, we design a mask-and-edge co-guided separable attention (MECSA) module, which consists of three flows for separately capturing edge, foreground, and background semantics. In addition, we propose a multi-scale enhancement fusion (MEF) module to aggregate multi-scale features of objects. The predictions are decoded in a top-down manner. Extensive experiments and visualizations demonstrate that our CNN-based and Transformer-based MECS-Net outperform 13 state-of-the-art methods on four popular COD datasets.

关键词： camouflaged object detection mask-and-edge co-guided multi-scale enhancement fusion

来源：评论

学校读者我要写书评

暂无评论

Depth awakens: A depth-perceptual attention fusion network for RGB-D camouflaged object detection

引用

IMAGE AND VISION COMPUTING 2024年 143卷

作者： Liu, Xinran Qi, Lin Song, Yuxuan Wen, Qi Ocean Univ China Dept Comp Sci & Technol Qingdao 266100 Peoples R China

camouflaged object detection (COD) presents a persistent challenge in accurately identifying objects that seamlessly blend into their surroundings. However, most existing COD models overlook the fact that visual systems operate within a genuine 3D environment. The scene depth inherent in a single 2D image provides rich spatial clues that can assist in the detection of camouflaged objects. Therefore, we propose a novel depthperception attention fusion network that leverages the depth map as an auxiliary input to enhance the network's ability to perceive 3D information, which is typically challenging for the human eye to discern from 2D images. The network uses a trident-branch encoder to extract chromatic and depth information and their communications. Recognizing that certain regions of a depth map may not effectively highlight the camouflaged object, we introduce a depth-weighted cross-attention fusion module to dynamically adjust the fusion weights on depth and RGB feature maps. To keep the model simple without compromising effectiveness, we design a straightforward feature aggregation decoder that adaptively fuses the enhanced aggregated features. Experiments demonstrate the significant superiority of our proposed method over other states of the arts, which further validates the contribution of depth information in camouflaged object detection. The code will be available at https://***/xinran-liu00/DAF-Net.

关键词： camouflaged object detection RGB-D Convolutional neural networks Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Mscnet: Mask stepwise calibration network for camouflaged object detection

引用

JOURNAL OF SUPERCOMPUTING 2024年第16期80卷 24718-24737页

作者： Du, Haishun Zhang, Minghao Zhang, Wenzhe Qiao, Kangyi Henan Univ Sch Artificial Intelligence Zhengzhou 450046 Peoples R China Int Joint Res Lab Cooperat Vehicular Networks Hena Zhengzhou 450046 Peoples R China

camouflaged object detection (COD) aims to accurately segment camouflaged objects blending into the environment and is a challenging task. Most existing deep learning-based COD methods do not explicitly enhance the region information of camouflaged objects, nor do they use the region information for mask calibration. To solve this issue, we propose a novel mask stepwise calibration network (MSCNet) for camouflaged object detection, which achieves high-precision detection of camouflaged objects. Specifically, MSCNet consists of a region information enhancement encoder and a mask stepwise calibration decoder. In the encoder, we first utilize a PVT backbone network to extract different levels of features from camouflaged images. Then, we design a region information enhancement module to enhance the region information of camouflaged objects while suppressing the interference of background information by mining, embedding, and aggregating the region information in different levels of features. In the decoder, we first design a coarse mask generation module to generate coarse prediction masks of camouflaged objects by directly cross-fusing different levels of features extracted by the backbone. In addition, we also design a mask calibration module to calibrate coarse prediction masks of camouflaged objects using the region information of different levels of camouflaged objects as a guide. Extensive experimental results on four benchmark datasets show that our method effectively identifies camouflaged objects and surpasses most state-of-the-art COD methods.

关键词： camouflaged object detection Region information enhancement Mask stepwise calibration camouflaged images

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Graph Interaction Transformer With Dynamic Token Clustering for camouflaged object detection

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 5936-5948页

作者： Yao, Siyuan Sun, Hao Xiang, Tian-Zhu Wang, Xiao Cao, Xiaochun Beijing Univ Posts & Telecommun Sch Comp Sci Natl Pilot Software Engn Sch Beijing 100876 Peoples R China Incept Inst Artificial Intelligence Abu Dhabi U Arab Emirates G42 Bayanat Abu Dhabi U Arab Emirates Beihang Univ Sch Software Beijing Peoples R China Sun Yat Sen Univ Sch Cyber Sci & Technol Shenzhen Campus Shenzhen 518107 Peoples R China

camouflaged object detection (COD) aims to identify the objects that seamlessly blend into the surrounding backgrounds. Due to the intrinsic similarity between the camouflaged objects and the background region, it is extremely challenging to precisely distinguish the camouflaged objects by existing approaches. In this paper, we propose a hierarchical graph interaction network termed HGINet for camouflaged object detection, which is capable of discovering imperceptible objects via effective graph interaction among the hierarchical tokenized features. Specifically, we first design a region-aware token focusing attention (RTFA) with dynamic token clustering to excavate the potentially distinguishable tokens in the local region. Afterwards, a hierarchical graph interaction transformer (HGIT) is proposed to construct bi-directional aligned communication between hierarchical features in the latent interaction space for visual semantics enhancement. Furthermore, we propose a decoder network with confidence aggregated feature fusion (CAFF) modules, which progressively fuses the hierarchical interacted features to refine the local detail in ambiguous regions. Extensive experiments conducted on the prevalent datasets, i.e. COD10K, CAMO, NC4K and CHAMELEON demonstrate the superior performance of HGINet compared to existing state-of-the-art methods.

关键词： Transformers Visualization Semantics object detection Focusing Computer vision Feature extraction Excavation Decoding Uncertainty camouflaged object detection graph interaction transformer dynamic token clustering

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：