Lightweight Salient Object Detection in Optical Remote Sensing Images via Feature Correlation

Li, Gongyang; Li, Zhi; Bai, Zhen; Wang, Lin; Ling, Haibin

doi:10.1109/tgrs.2022.3145483

Cited by 65 publications

(32 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For ORSI-SOD, Li et al [15] proposed the first lightweight method, i.e., CorrNet. They lightened the vanilla VGG-16 [42] for efficient feature extraction, and adopted the coarse-tofine strategy to detect salient objects in ORSIs with dense lightweight refinement blocks.…”

Section: Lightweight Salient Object Detectionmentioning

confidence: 99%

“…Saliency maps produced by four types of methods and our method on ORSIs. PA-KRN [12] is an NSI-SOD method, HVPNet [13] is a lightweight NSI-SOD method, MCCNet [14] is an ORSI-SOD method, and CorrNet [15] is a lightweight ORSI-SOD method. Please zoom-in for details.…”

Section: Introductionmentioning

confidence: 99%

“…For the lightweight ORSI-SOD method, as shown in the penultimate column of Fig. 1, CorrNet [15] significantly reduces the amount of parameters and achieves good performance, but still consumes a lot of computational cost.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment

Zhang

et al. 2023

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

Recently, relying on convolutional neural networks (CNNs), many methods for salient object detection in optical remote sensing images (ORSI-SOD) are proposed. However, most methods ignore the huge parameters and computational cost brought by CNNs, and only a few pay attention to the portability and mobility. To facilitate practical applications, in this paper, we propose a novel lightweight network for ORSI-SOD based on semantic matching and edge alignment, termed SeaNet. Specifically, SeaNet includes a lightweight MobileNet-V2 for feature extraction, a dynamic semantic matching module (DSMM) for high-level features, an edge self-alignment module (ESAM) for low-level features, and a portable decoder for inference. First, the high-level features are compressed into semantic kernels. Then, semantic kernels are used to activate salient object locations in two groups of high-level features through dynamic convolution operations in DSMM. Meanwhile, in ESAM, cross-scale edge information extracted from two groups of low-level features is self-aligned through L2 loss and used for detail enhancement. Finally, starting from the highest-level features, the decoder infers salient objects based on the accurate locations and fine details contained in the outputs of the two modules. Extensive experiments on two public datasets demonstrate that our lightweight SeaNet not only outperforms most state-of-the-art lightweight methods but also yields comparable accuracy with state-of-theart conventional methods, while having only 2.76M parameters and running with 1.7G FLOPs for 288×288 inputs. Our code and results are available at https://github.com/MathLee/SeaNet.

show abstract

Section: Lightweight Salient Object Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment

Zhang

et al. 2023

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…And cross-modal RGB and TIR features are complementary, which is more conducive to locating objects. Inspired by the object segmentation works which explore the correlation (i.e., co-attention [61]) of target objects in consecutive video frames [36] (i.e., cross-frame) and features of successive levels [37] (i.e., cross-level), we propose Collaborative Location Module to model the pixel-level correlation of cross-modal high-level semantic features to collaboratively determine the object location. In addition, we mine the valuable representation from two types of feature combinations (i.e., summation and multiplication) in the CLM.…”

Section: B Collaborative Location Modulementioning

confidence: 99%

“…Specifically, we divide the basic cross-modal features extracted by the backbone into three levels, i.e., high, middle, and low levels. For high-level features, we propose a Collaborative Location Module (CLM), which builds pixellevel correlations [36], [37] among semantic representations to locate all potential objects. For middle-level features, we propose a Complementary Activation Module (CAM), which builds on the attention mechanism [12], [38] to generate informative features for exact region activation.…”

Section: Introductionmentioning

confidence: 99%

RGB-T Semantic Segmentation With Location, Activation, and Sharpening

Wang

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Semantic segmentation is important for scene understanding. To address the scenes of adverse illumination conditions of natural images, thermal infrared (TIR) images are introduced. Most existing RGB-T semantic segmentation methods follow three cross-modal fusion paradigms, i.e., encoder fusion, decoder fusion, and feature fusion. Some methods, unfortunately, ignore the properties of RGB and TIR features or the properties of features at different levels. In this paper, we propose a novel feature fusion-based network for RGB-T semantic segmentation, named LASNet, which follows three steps of location, activation, and sharpening. The highlight of LASNet is that we fully consider the characteristics of cross-modal features at different levels, and accordingly propose three specific modules for better segmentation. Concretely, we propose a Collaborative Location Module (CLM) for high-level semantic features, aiming to locate all potential objects. We propose a Complementary Activation Module for middle-level features, aiming to activate exact regions of different objects. We propose an Edge Sharpening Module (ESM) for lowlevel texture features, aiming to sharpen the edges of objects. Furthermore, in the training phase, we attach a location supervision and an edge supervision after CLM and ESM, respectively, and impose two semantic supervisions in the decoder part to facilitate network convergence. Experimental results on two public datasets demonstrate that the superiority of our LASNet over relevant state-of-the-art methods. The code and results of our method are available at https://github.com/MathLee/LASNet.

show abstract

Research on salient object detection algorithm for complex electrical components

Tian,

Zeng,

Hong

et al. 2024

J Intell Manuf

View full text Add to dashboard Cite

Lightweight Salient Object Detection in Optical Remote Sensing Images via Feature Correlation

Cited by 65 publications

References 63 publications

Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment

Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment

RGB-T Semantic Segmentation With Location, Activation, and Sharpening

Research on salient object detection algorithm for complex electrical components

Contact Info

Product

Resources

About