MANet: Multi-Scale Aware-Relation Network for Semantic Segmentation in Aerial Scenes

He, Pei; Jiao, Licheng; Shang, Ronghua; Wang, Shuang; Liu, Xu; Quan, Dou; Yang, Kun; Zhao, Dong

doi:10.1109/tgrs.2022.3179379

Cited by 21 publications

(8 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Backbone Complexity(G) Parameters(M) Speed(FPS) SegFormer [5] Mit-B1 63.3 13.7 31.3 BiSeNet [8] ResNet18 51.8 12.9 121.9 MANet [9] ResNet18 51.7 12.0 75.6 UNetformer [6] ResNet18 46.9 11.7 115.6 GDformer ResNet18 46.4 11.5 136.0…”

Section: Methodsmentioning

confidence: 99%

GDformer: a lightweight decoder for efficient semantic segmentation of remote sensing urban scene imagery

Liu,

Zhong

2024

Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023)

View full text Add to dashboard Cite

Semantic segmentation of remote sensing urban scene imagery is a dense prediction task, which has been applied to the land-cover or land-use category. However, the dimension of remote sensing image is huge, which will result in the huge computation cost. In order to reduce the computation cost, a common method is to design a lightweight decoder to achieve a good trade-off between accuracy and computation cost. For this purpose, we design a lightweight transformer-based decoder GDformer. The GDformer consists of our proposed Global Value Transformer and Dynamic feature fusion module. The Global Value Transformer can extract the global semantic feature and the Dynamic feature fusion module can fuse the local feature and global semantic feature dynamic to capture the local-global context with a good trade-off, and the local-global context has been proved is necessary for the semantic segmentation of remote sensing. Extensive experiments prove that our proposed method can achieve a good trade-off between and state-of-the-art performance.

show abstract

Section: Methodsmentioning

confidence: 99%

GDformer: a lightweight decoder for efficient semantic segmentation of remote sensing urban scene imagery

Liu,

Zhong

2024

Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023)

View full text Add to dashboard Cite

show abstract

“…To demonstrate the advantages of the proposed method in defending against poisoning attacks and completing accurate semantic segmentation, we compare the proposed method with several state-of-the-art methods, including the CNNs-based methods and the Transformer-based methods. For the CNNs-based methods, the proposed RIFENet is compared with AFNet [69], SBANet [70], MANet [71], SSAtNet [72], and HFGNet [25]. For the Transformer-based methods, RIFENet is compared with STUFormer [73], EMRFormer [74], CONFormer [75], ATTFormer [76], and DSegFormer [77].…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…MANet [71]: This network uses discriminative feature learning to obtain fine-grained feature information and uses the multi-scale feature calibration module to filter redundant features to enhance feature representation. 4.…”

mentioning

confidence: 99%

Defending against Poisoning Attacks in Aerial Image Semantic Segmentation with Robust Invariant Feature Enhancement

Wang

Zhang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The outstanding performance of deep neural networks (DNNs) in multiple computer vision in recent years has promoted its widespread use in aerial image semantic segmentation. Nonetheless, prior research has demonstrated the high susceptibility of DNNs to adversarial attacks. This poses significant security risks when applying DNNs to safety-critical earth observation missions. As an essential means of attacking DNNs, data poisoning attacks destroy model performance by contaminating model training data, allowing attackers to control prediction results by carefully crafting poisoning samples. Toward building a more robust DNNs-based aerial image semantic segmentation model, in this study, we proposed a robust invariant feature enhancement network (RIFENet) that can resist data poisoning attacks and has superior semantic segmentation performance. The constructed RIFENet improves the resistance to poisoning attacks by extracting and enhancing robust invariant features. Specifically, RIFENet uses a texture feature enhancement module (T-FEM), structural feature enhancement module (S-FEM), global feature enhancement module (G-FEM), and multi-resolution feature fusion module (MR-FFM) to enhance the representation of different robust features in the feature extraction process to suppress the interference of poisoning samples. Experiments on several benchmark aerial image datasets demonstrate that the proposed method is more robust and exhibits better generalization than other state-of-the-art methods.

show abstract

“…It takes into account the effects of depth, width, and resolution factors and combines them to form the series of efficientnet. We chose the efficientnet-b1 network [34] as the backbone, while the number of channels for each layer of outputs is (24,40,112,320), and the number of MBConv basic modules used in each layer is (5, 3, 8, 7).…”

Section: Efficientnet As Encodermentioning

confidence: 99%

OESA-UNet: An Adaptive and Attentional Network for Detecting Diverse Magnetopause under the Limited Field of View

Wang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Imaging has been an important strategy for exploring space weather. The Solar wind Magnetosphere Ionosphere Link Explorer (SMILE) is a joint Chinese Academy of Sciences (CAS) and European Space Agency (ESA) mission, aiming at studying the interaction between Earth’s magnetosphere and solar wind near the subsolar point via soft X-ray imaging. As the boundary of Earth’s magnetosphere, magnetopause is a significant detection target to mirror solar wind’s change for the SMILE mission. In preparation for inverting three-dimensional magnetopause, we proposed an OESA-UNet model to detect the magnetopause position. The model obtains magnetopause with a U-shaped structure, in an end-to-end manner. Inspired by attention mechanisms, these blocks are integrated into ours. OESA-UNet captures low and high-level feature maps by adjusting the receptive field for precise localization. Adaptively pre-processing the image provides a prior for the network. Availability metrics are designed to determine whether it can serve three-dimensional inversion. Lastly, we provided ablation and comparison experiments by qualitative and quantitative analysis. Our recall, precision, and f1 score are 93.8%, 92.1%, and 92.9%, respectively, with an average angle deviation of 0.005 under the availability metrics. Results indicate that OESA-UNet outperforms other methods. It can better serve the purpose of magnetopause tracing from an X-ray image.

show abstract

MANet: Multi-Scale Aware-Relation Network for Semantic Segmentation in Aerial Scenes

Cited by 21 publications

References 63 publications

GDformer: a lightweight decoder for efficient semantic segmentation of remote sensing urban scene imagery

GDformer: a lightweight decoder for efficient semantic segmentation of remote sensing urban scene imagery

Defending against Poisoning Attacks in Aerial Image Semantic Segmentation with Robust Invariant Feature Enhancement

OESA-UNet: An Adaptive and Attentional Network for Detecting Diverse Magnetopause under the Limited Field of View

Contact Info

Product

Resources

About