LFRNet: Localizing, Focus, and Refinement Network for Salient Object Detection of Surface Defects

Wan, Bin; Zhou, Xiaofei; Zheng, Bolun; Yin, Haibing; Zhu, Zunjie; Wang, Hongkui; Sun, Yaoqi; Zhang, Jiyong; Yan, Chenggang

doi:10.1109/tim.2023.3250302

Cited by 18 publications

(3 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Salient objects are regions in the image that attract attention and are significantly different from the surrounding environment. In recent years, deep learning has been widely applied in the field of SOD, with many scholars aiming to improve the accuracy of SOD through various methods such as attention mechanisms [16], focusing on object edges [17] and multi-scale or multi-level feature fusion [18,19]. However, unlike the human visual mechanism, there are significant differences between camouflaged objects and salient objects; hence, SOD methods cannot be directly applied to the detection of camouflaged objects.…”

Section: Related Workmentioning

confidence: 99%

Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation

Wang,

Li,

Wei

et al. 2024

Electronics

View full text Add to dashboard Cite

The existence of camouflage targets is widespread in the natural world, as they blend seamlessly or closely resemble their surrounding environment, making it difficult for the human eye to identify them accurately. In camouflage target segmentation, challenges often arise from the high similarity between the foreground and background, resulting in segmentation errors, imprecise edge detection, and overlooking of small targets. To address these issues, this paper presents a robust localization-guided dual-branch network for the recognition of camouflaged targets. Two crucial branches, i.e., a localization branch and an overall refinement branch are designed and incorporated. The localization branch achieves accurate preliminary localization of camouflaged targets by incorporating the robust localization module, which integrates different high-level feature maps in a partially decoded manner. The overall refinement branch optimizes segmentation accuracy based on the output predictions of the localization branch. Within this branch, the edge refinement module is devised to effectively reduce false negative and false positive interference. By conducting context exploration on each feature layer from top to bottom, this module further enhances the precision of target edge segmentation. Additionally, our network employs five jointly trained output prediction maps and introduces attention-guided heads for diverse prediction maps in the overall refinement branch. This design adjusts the spatial positions and channel weights of different prediction maps, generating output prediction maps based on the emphasis of each output, thereby further strengthening the perception and feature representation capabilities of the model. To improve its ability to generate highly confident and accurate prediction candidate regions, tailored loss functions are designed to cater to the objectives of different prediction maps. We conducted experiments on three publicly available datasets for camouflaged object detection to assess our methodology and compared it with state-of-the-art network models. On the largest dataset COD10K, our method achieved a Structure-measure of 0.827 and demonstrated superior performance in other evaluation metrics, outperforming recent network models.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation

Wang,

Li,

Wei

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…RGB SOD has been popular for quite some time now and aims at detecting salient objects from a single RGB image [14]. Conventional models mainly design some handcrafted features or employ some prior knowledge (e.g.…”

Section: A Rgb Sodmentioning

confidence: 99%

“…As shown in Table I, we conduct a comparative analysis of our proposed AM model with several state-of-theart SOD models, including RGB SOD models(PSGLoss [31], PoolNet++ [32] and SefReFormer [33]), RGB-D SOD models (VST(2022) [34], SwinNet(2022) [22], CAVER(2023) [23]), RGB-T SOD models (APNet(2022) [35], FANet(2023) [36] and LSNet(2023) [37]), and RGB-D-T SOD models(HWSI(2023) [8] and MFFNet(2023) [38]). It's worth noting that those RGB-T SOD and RGB-D SOD models actually train their models on both RGB-T SOD and RGB-D SOD datasets, respectively, i.e.…”

Section: Quantitative Comparisons With Sota Modelsmentioning

confidence: 99%

Employing Bilinear Fusion and Saliency Prior Information for RGB-D Salient Object Detection

Huang

Yang

Zhang

et al. 2022

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Multi-modal feature fusion and saliency reasoning are two core sub-tasks of RGB-D salient object detection. However, most existing models employ linear fusion strategies (e.g., concatenation) for multi-modal feature fusion and use a simple coarse-to-fine structure for saliency reasoning. Despite their simpleness, they can neither fully capture the cross-modal complementary information nor exploit the multi-level complementary information among the cross-modal features at different levels. To address these issues, a novel RGB-D salient object detection model is presented, where we pay special attention to the aforementioned two sub-tasks. Concretely, a multi-modal feature interaction module is first presented to explore more interactions between the unimodal RGB and depth features. It helps to capture their cross-modal complementary information by jointly using some simple linear fusion strategies and bilinear fusion ones. Then, a saliency prior information guided fusion module is presented to exploit the multi-level complementary information among the fused cross-modal features at different levels. Instead of employing a simple convolutional layer for the final saliency prediction, a saliency refinement and prediction module is designed to better exploit those extracted multilevel cross-modal information for RGB-D saliency detection. Experimental results on several benchmark datasets verify the effectiveness and superiority of the proposed framework over some state-of-the-art methods.Index Terms-RGB-D salient object detection, bilinear fusion strategy, saliency prior information guided fusion, saliency refinement and prediction. [9] and segmentation [10]. Benefiting from the progress of Convolutional Neural Networks (CNNs), CNNs based RGB SOD models [2], [11], [12], [13] have significantly improved the performance of conventional hand-crafted feature based approaches [14], [15], [16], [17].However, such algorithms are found vulnerable to complex environments, varying illuminations or cluttered backgrounds. After paying a lot of efforts, researchers realize that using RGB images only cannot solve those challenges. Meanwhile,

show abstract

Adversarial-based refinement dual-branch network for semi-supervised salient object detection of strip steel surface defects

Sun,

Zhang,

Liu

2024

Vis Comput

View full text Add to dashboard Cite

LFRNet: Localizing, Focus, and Refinement Network for Salient Object Detection of Surface Defects

Cited by 18 publications

References 68 publications

Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation

Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation

Employing Bilinear Fusion and Saliency Prior Information for RGB-D Salient Object Detection

Adversarial-based refinement dual-branch network for semi-supervised salient object detection of strip steel surface defects

Contact Info

Product

Resources

About