Multiscale Feature Enhancement Network for Salient Object Detection in Optical Remote Sensing Images

Wang, Zhen; Guo, Jianxin; Zhang, Chuanlei; Wang, Buhong

doi:10.1109/tgrs.2022.3224815

Cited by 66 publications

(14 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, this paper sets up three groups of submarine maneuvering state inversion simulation experiments. The effectiveness of the proposed method is verified by comparing the results of submarine maneuverability state inversion with MFENet [ 44 ], SA-SPPN [ 45 ], DAFNet [ 46 ], and APAN [ 47 ] algorithms. The evaluation criteria of the algorithm are mean average accuracy (mAP) and overall accuracy (Acc).…”

Section: Experimental Results and Analysismentioning

confidence: 99%

An Improved Wake Vortex-Based Inversion Method for Submarine Maneuvering State

Kong

Yang

Cai

et al. 2023

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

As the noise reduction performance of submarines continues to improve, it is difficult to detect and track submarines through acoustic detection techniques. Therefore, nonacoustic submarine detection techniques are becoming more and more important. The submarine movement will leave a wake vortex, and the information of the wake vortex can be used to invert the maneuvering state of the submarine. However, the wake vortex is constantly dissipated in the evolution process, and the strength of the wake vortex is constantly reduced, resulting in the gradual weakening of the characteristics of the wake vortex, which makes the inversion of submarine operating state difficult and less accurate. In order to solve the above problems, this paper proposes an improved wake vortex-based inversion method for submarine maneuvering state. Firstly, a random finite set of submarine wake vortex observation features is established to obtain the feature with the highest correlation degree with submarine maneuvering state in the random finite set. Secondly, the multiscale fusion module and attention mechanism are used to re-encode the weak features of the wake vortex image, and the salient features of the wake vortex image are extracted. Finally, the manipulation state of the wake vortex image is retrieved by the extracted salient features. The experimental results show that the average inversion accuracy of the proposed algorithm is improved by 1.27% in terms of manipulating state inversion of weak feature wake vortex images. The algorithm in this paper can realize the inversion of submarine maneuvering state in the case of weak submarine wake vortex image features and incomplete feature information. It provides the basis for the detection technology based on the submarine wake characteristics.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

An Improved Wake Vortex-Based Inversion Method for Submarine Maneuvering State

Kong

Yang

Cai

et al. 2023

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…(2) CNN-Transformer based hybrid models [8][9][10]16,33,34], designed to adequately learn diverse target features are proposed. For example, the ASNet network proposed in [8] innovatively integrates Transformer and CNN techniques in a two-branch encoder to capture global dependencies while capturing local fine-grained image features.…”

Section: Methods Based On Network Designmentioning

confidence: 99%

“…In recent years, many studies have proposed the combination of deep learning and edge detection to guide the model to better perceive the cropland information, improve the local segmentation score accuracy, and maintain the global morphology land continuity. Existing approaches [2,4,[7][8][9][10][11][12][13][14][15][16] designspecific network structures based on the characteristics of Cropland to guide the model to focus on key features. However, most of them focus on specific geographic regions or a single cropland type, ignoring the regional differences of cropland parcels, and failing to achieve the purpose of generalized extraction.…”

Section: Introductionmentioning

confidence: 99%

BAFormer: A Novel Boundary-Aware Compensation UNet-like Transformer for High-Resolution Cropland Extraction

Li,

Wang,

Tian

et al. 2024

Preprint

View full text Add to dashboard Cite

Utilizing deep learning for semantic segmentation of cropland from remote sensing imagery has become a crucial technique in land surveys. Cropland illustrates diverse morphologies and degrees of fragmentation on the Earth’s surface, underscoring the importance of accurately perceiving the complex boundaries of cropland which are crucial for effective segmentation. This paper introduces a UNet-like boundary-aware compensation model BAFormer. Cropland boundaries typically exhibit rapid transformations in pixel values and texture features, often appearing as high-frequency features in remote-sensing images. To enhance the recognition of these high-frequency features as represented by cropland boundaries, the proposed BAFormer integrates a Feature Adaptive Mixer (FAM) and develops a Deep Wide Large Kernel Multi-Layer Perceptron (DWLK-MLP) to enrich the global and local cropland boundaries features separately. Specifically, FAM adaptively mixes high-frequency and low-frequency features through the advantages of convolution and self-attention; DWLK-MLP expands the convolutional receptive field by deeply decomposing large kernel convolutions. The efficacy of BAFormer has been evaluated on the Vaihingen, Potsdam, and LoveDA public datasets, as well as the Mapcup dataset. It has demonstrated advanced performance, achieving mIoU scores of 84.5%, 87.3%, 53.5%, and 83.1% on these datasets respectively. Notably, BAFormer-T, the lightweight iteration of the model, surpasses other lightweight models on the Vaihingen dataset with scores of 91.3% F1 and 84.1% mIoU. The source code is available at https://github.com/WangYouM1999/BAFormer.

show abstract

“…CCFENet [20] proposes an essential cross-collaboration enhancement strategy (CCE), which facilitates the interactions when encoding. HFANet [21] jointly models boundary learning to salient object detection, addressing the issue of cluttered backgrounds, scale invariance, complicated edges, and irregular topology. It extracts abundant context in the deep semantic features using Gated Fold-ASPP, integrating adjacent features with an unparameterized alignment strategy by AFAM.…”

Section: Salient Object Detection Researchmentioning

confidence: 99%

Application of Split Coordinate Channel Attention Embedding U2Net in Salient Object Detection

Wu,

2024

Algorithms

View full text Add to dashboard Cite

Salient object detection (SOD) aims to identify the most visually striking objects in a scene, simulating the function of the biological visual attention system. The attention mechanism in deep learning is commonly used as an enhancement strategy which enables the neural network to concentrate on the relevant parts when processing input data, effectively improving the model’s learning and prediction abilities. Existing saliency object detection methods based on RGB deep learning typically treat all regions equally by using the extracted features, overlooking the fact that different regions have varying contributions to the final predictions. Based on the U2Net algorithm, this paper incorporates the split coordinate channel attention (SCCA) mechanism into the feature extraction stage. SCCA conducts spatial transformation in width and height dimensions to efficiently extract the location information of the target to be detected. While pixel-level semantic segmentation based on annotation has been successful, it assigns the same weight to each pixel which leads to poor performance in detecting the boundary of objects. In this paper, the Canny edge detection loss is incorporated into the loss calculation stage to improve the model’s ability to detect object edges. Based on the DUTS and HKU-IS datasets, experiments confirm that the proposed strategies effectively enhance the model’s detection performance, resulting in a 0.8% and 0.7% increase in the F1-score of U2Net. This paper also compares the traditional attention modules with the newly proposed attention, and the SCCA attention module achieves a top-three performance in prediction time, mean absolute error (MAE), F1-score, and model size on both experimental datasets.

show abstract

Multiscale Feature Enhancement Network for Salient Object Detection in Optical Remote Sensing Images

Cited by 66 publications

References 53 publications

An Improved Wake Vortex-Based Inversion Method for Submarine Maneuvering State

An Improved Wake Vortex-Based Inversion Method for Submarine Maneuvering State

BAFormer: A Novel Boundary-Aware Compensation UNet-like Transformer for High-Resolution Cropland Extraction

Application of Split Coordinate Channel Attention Embedding U2Net in Salient Object Detection

Contact Info

Product

Resources

About