Boundary guidance network for camouflage object detection

Xu, Xiuqi; Zhu, Mingyu; Yu, Jinhao; Chen, Shuhan; Hu, Xuelong; Yang, Yuequan

doi:10.1016/j.imavis.2021.104283

Cited by 22 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of patterns and regions varied up to 24 and 9, respectively in this analysis. The methods BGN-COD [11], and ERR-Net [13] are used along the proposed scheme in this comparative analysis.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Linear Differentiation Scheme for Camouflaged Target Detection using Convolution Neural Networks

Sambbantham,

Balasubramanian,

Rajarathnam

et al. 2023

RAiSE-2023

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

“…Xu et al [11] designed a new boundary guidance network for camouflage object detection (COD). A localization decoder is implemented in the method to capture multiscale information for further processes.…”

Section: Related Workmentioning

confidence: 99%

A Linear Differentiation Scheme for Camouflaged Target Detection using Convolution Neural Networks

Sambbantham,

Balasubramanian,

Rajarathnam

et al. 2023

RAiSE-2023

View full text Add to dashboard Cite

show abstract

“…Remarkable works were proposed to generate the boundary map first, and then use the boundary map as the guidance of the encoder [28], [29] and the decoder [30], [31], or use both the coarse region map and boundary map as the guidance of the followup decoder [32] for better COD performance. In addition, to help the network focus more on boundary details, a recent attempt also predicted the object regions and boundary cues progressively at multiple stages of the decoder [33].…”

Section: Introductionmentioning

confidence: 99%

Dual-Constraint Coarse-to-Fine Network for Camouflaged Object Detection

Yue,

Xiao,

Xie

et al. 2024

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Camouflaged object detection (COD) is an important yet challenging task, with great application values in industrial defect detection, medical care, etc. The challenges mainly come from the high intrinsic similarities between target objects and background. In this paper, inspired by the biological studies that object detection consists of two steps, i.e., search and identification, we propose a novel framework, named DCNet, for accurate COD. DCNet explores candidate objects and extra object-related edges through two constraints (object area and boundary) and detects camouflaged objects in a coarse-to-fine manner. Specifically, we first exploit an area-boundary decoder (ABD) to obtain initial region cues and boundary cues simultaneously by fusing multi-level features of the backbone. Then, an area search module (ASM) is embedded into each level of the backbone to adaptively search coarse regions of objects with the assistance of region cues from the ABD. After the ASM, an area refinement module (ARM) is utilized to identify fine regions of objects by fusing adjacent-level features with the guidance of boundary cues. Through the deep supervision strategy, DCNet can finally localize the camouflaged objects precisely. Extensive experiments on three benchmark COD datasets demonstrate that our DCNet is superior to 12 state-of-the-art COD methods. In addition, DCNet shows promising results on two COD-related tasks, i.e., industrial defect detection and polyp segmentation.

show abstract

“…I N nature, numerous wild animals strive to seamlessly blend into their surroundings, adapting to the environment [1]- [4].Camouflage, as an effective technique for deceiving the observer's visual perceptual system, is widely adopted by prey to minimize the risk of detection by predators [5]. Targeting the identification of objects with a similar appearance to the background, Camouflaged Object Detection (COD) has garnered significant attention [6]- [8]. Serving as a fundamental pre-processing approach, COD has not only captured growing research interest but has also catalyzed advancements in various computer vision tasks, such as polyp segmentation [9], lung infection segmentation [10], defect detection [11], recreational art [12], and transparent object detection [13].…”

Section: Introductionmentioning

confidence: 99%

“…Consequently, these methods frequently encounter challenges related to fuzzy boundaries. Secondly, most approaches [1]- [3], [6]- [8] adhere to the encoder-decoder framework, in which a single decoder is employed to consolidate multi-level features extracted from the encoder. Typically, during the decoder stage, high-level features are transmitted to shallower levels to pinpoint the targets and suppress background noise.…”

Section: Introductionmentioning

confidence: 99%

Detecting Camouflaged Objects via Multi-Stage Coarse-to-Fine Refinement

Wang,

Chen,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Camouflaged objects are typically assimilated into their surroundings. Consequently, in contrast to generic object detection/segmentation, camouflaged object detection proves to be considerably more intricate due to the indistinct boundaries and heightened intrinsic similarities between foreground targets and the surrounding environment. Despite the proposition of numerous algorithms that have demonstrated commendable performance across various scenarios, these approaches may still grapple with blurred boundaries, leading to the inadvertent omission of camouflaged targets in challenging scenes. In this paper, we introduce a multi-stage framework tailored for segmenting camouflaged objects through a process of coarse-to-fine refinement. Specifically, our network encompasses three distinct decoders, each fulfilling a unique role in the model. In the initial decoder, we introduce the Bi-directional Locating Module to excavate foreground and background cues, enhancing target localization. The second decoder focuses on leveraging boundary information to augment overall performance, incorporating the Multi-level Feature Fusion Module to generate prediction maps with finer boundaries. Subsequently, the third decoder introduces the Maskguided Fusion Module, designed to process high-resolution features under the guidance of the second decoder's results. This approach enables the preservation of structural details and the generation of finegrained prediction maps. Through the integration of the three decoders, our model effectively identifies and segments camouflaged targets. Extensive experiments are conducted on three commonly used benchmark datasets. The results of these experiments demonstrate that, even without the application of pre-processing or post-processing techniques, our model outperforms 14 state-of-the-art algorithms. INDEX TERMSCamouflaged object detection, coarse-to-fine refinement, convolutional neural network, multi-stage detection. Recently, with the rapid development of Convolutional Neural Networks (CNNs), researchers have endeavored to construct CNN-based models to address the COD problem. Diverging from early traditional hard-crafted methods, CNN-based approaches can simultaneously exploit low-level

show abstract

Boundary guidance network for camouflage object detection

Cited by 22 publications

References 9 publications

A Linear Differentiation Scheme for Camouflaged Target Detection using Convolution Neural Networks

A Linear Differentiation Scheme for Camouflaged Target Detection using Convolution Neural Networks

Dual-Constraint Coarse-to-Fine Network for Camouflaged Object Detection

Detecting Camouflaged Objects via Multi-Stage Coarse-to-Fine Refinement

Contact Info

Product

Resources

About