FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312853890> ?p ?o ?g. }

• W4312853890 endingPage "134251" @default.
• W4312853890 startingPage "134241" @default.
• W4312853890 abstract "As the largest target in remote sensing images, buildings have important application value in urban planning and old city reconstruction. However, most networks have poor recognition ability on high resolution images, resulting in blurred boundaries in the segmented building maps. Then, the similarity between buildings and backgrounds will lead to inter-class indistinction. Finally, the diversity of buildings brings difficulties to segmentation, which requires the network to have better generalization ability. To address these problems, we propose Fusion Multi-scale Attention Mechanism Network (FMAM-Net). Firstly, we design Feature Refine Compensation Module(FRCM) to improve the boundary ambiguity problem, including Feature Refinement Module(FRM) and Feature Compensation Module(FCM). FRM utilizes the densely connected architecture to refine features and increase recognition capabilities. FCM introduces low-level features to make up for the lack of boundary information in high-level features. Secondly, to handle inter-class indistinction, we design Tandem Attention Module(TAM) and Parallel Attention Module(PAM). TAM is designed to sequentially filter some features from channels and spaces for adaptive feature refinement. PAM combines context information and uses high-level features to guide low-level features to select more distinguishable features. Finally, based on the binary cross entropy loss function, we add an evaluation index to reduce the error caused by determining the optimization direction only through cross entropy. On the Inria Aerial Image Labeling Dataset, FMAM-Net achieves mean IoU of 85.34%, which is 5.58% higher than AMUNet and 3.77% higher than our baseline(U-Net ResNet-34). On the WHU Dataset, IoU reached the maximum value of 91.06% on FMAM-Net, 1.67% higher than SARB-UNet and 0.2% higher than MAP-Net. The visualization results show that FMAM-Net improves the fuzzy boundary of building segmentation and reduces the inter-class indistinction." @default.
• W4312853890 created "2023-01-05" @default.
• W4312853890 creator A5003127462 @default.
• W4312853890 creator A5005042323 @default.
• W4312853890 creator A5042443239 @default.
• W4312853890 creator A5089056035 @default.
• W4312853890 date "2022-01-01" @default.
• W4312853890 modified "2023-10-10" @default.
• W4312853890 title "FMAM-Net: Fusion Multi-Scale Attention Mechanism Network for Building Segmentation in Remote Sensing Images" @default.
• W4312853890 cites W1536680647 @default.
• W4312853890 cites W1986744422 @default.
• W4312853890 cites W2006015451 @default.
• W4312853890 cites W2183182206 @default.
• W4312853890 cites W2412782625 @default.
• W4312853890 cites W2609402060 @default.
• W4312853890 cites W2774320778 @default.
• W4312853890 cites W2787614951 @default.
• W4312853890 cites W2799166040 @default.
• W4312853890 cites W2806808924 @default.
• W4312853890 cites W2884436604 @default.
• W4312853890 cites W2908320224 @default.
• W4312853890 cites W2920326761 @default.
• W4312853890 cites W2922544158 @default.
• W4312853890 cites W2963150697 @default.
• W4312853890 cites W2963446712 @default.
• W4312853890 cites W2966450079 @default.
• W4312853890 cites W2967087542 @default.
• W4312853890 cites W2972623730 @default.
• W4312853890 cites W2982206001 @default.
• W4312853890 cites W2996413893 @default.
• W4312853890 cites W3003682051 @default.
• W4312853890 cites W3011515952 @default.
• W4312853890 cites W3015788359 @default.
• W4312853890 cites W3036062910 @default.
• W4312853890 cites W3053564872 @default.
• W4312853890 cites W3154205755 @default.
• W4312853890 cites W3157192212 @default.
• W4312853890 cites W3168588044 @default.
• W4312853890 cites W3174867596 @default.
• W4312853890 cites W3190860548 @default.
• W4312853890 cites W3197957534 @default.
• W4312853890 cites W4205457644 @default.
• W4312853890 cites W4210862552 @default.
• W4312853890 cites W4213275769 @default.
• W4312853890 cites W4307726656 @default.
• W4312853890 cites W4312716506 @default.
• W4312853890 cites W4312981890 @default.
• W4312853890 doi "https://doi.org/10.1109/access.2022.3231362" @default.
• W4312853890 hasPublicationYear "2022" @default.
• W4312853890 type Work @default.
• W4312853890 citedByCount "0" @default.
• W4312853890 crossrefType "journal-article" @default.
• W4312853890 hasAuthorship W4312853890A5003127462 @default.
• W4312853890 hasAuthorship W4312853890A5005042323 @default.
• W4312853890 hasAuthorship W4312853890A5042443239 @default.
• W4312853890 hasAuthorship W4312853890A5089056035 @default.
• W4312853890 hasConcept C106301342 @default.
• W4312853890 hasConcept C121332964 @default.
• W4312853890 hasConcept C124101348 @default.
• W4312853890 hasConcept C124504099 @default.
• W4312853890 hasConcept C138885662 @default.
• W4312853890 hasConcept C151730666 @default.
• W4312853890 hasConcept C153180895 @default.
• W4312853890 hasConcept C154945302 @default.
• W4312853890 hasConcept C167981619 @default.
• W4312853890 hasConcept C2776401178 @default.
• W4312853890 hasConcept C2779343474 @default.
• W4312853890 hasConcept C31972630 @default.
• W4312853890 hasConcept C41008148 @default.
• W4312853890 hasConcept C41895202 @default.
• W4312853890 hasConcept C62520636 @default.
• W4312853890 hasConcept C86803240 @default.
• W4312853890 hasConcept C89600930 @default.
• W4312853890 hasConceptScore W4312853890C106301342 @default.
• W4312853890 hasConceptScore W4312853890C121332964 @default.
• W4312853890 hasConceptScore W4312853890C124101348 @default.
• W4312853890 hasConceptScore W4312853890C124504099 @default.
• W4312853890 hasConceptScore W4312853890C138885662 @default.
• W4312853890 hasConceptScore W4312853890C151730666 @default.
• W4312853890 hasConceptScore W4312853890C153180895 @default.
• W4312853890 hasConceptScore W4312853890C154945302 @default.
• W4312853890 hasConceptScore W4312853890C167981619 @default.
• W4312853890 hasConceptScore W4312853890C2776401178 @default.
• W4312853890 hasConceptScore W4312853890C2779343474 @default.
• W4312853890 hasConceptScore W4312853890C31972630 @default.
• W4312853890 hasConceptScore W4312853890C41008148 @default.
• W4312853890 hasConceptScore W4312853890C41895202 @default.
• W4312853890 hasConceptScore W4312853890C62520636 @default.
• W4312853890 hasConceptScore W4312853890C86803240 @default.
• W4312853890 hasConceptScore W4312853890C89600930 @default.
• W4312853890 hasFunder F4320324867 @default.
• W4312853890 hasFunder F4320325436 @default.
• W4312853890 hasLocation W43128538901 @default.
• W4312853890 hasOpenAccess W4312853890 @default.
• W4312853890 hasPrimaryLocation W43128538901 @default.
• W4312853890 hasRelatedWork W1522196789 @default.
• W4312853890 hasRelatedWork W2086372684 @default.
• W4312853890 hasRelatedWork W2501551404 @default.

• next