Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379877582> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4379877582 endingPage "103363" @default.
- W4379877582 startingPage "103363" @default.
- W4379877582 abstract "Semantic segmentation, a fundamental research direction in synthetic aperture radar (SAR) image interpretation, has significant application value for multiple sectors. However, noise, multi-style terrains, geometric distortion, and shadows make SAR image segmentation challenging. Although existing deep learning algorithms tend to mine the semantic relationship between pixels within individual images, they disregard the global context of the training data and the semantic relationship between different regions from different images. Moreover, the noise resistance of the networks is not strong enough. All of these factors degrade the performance of SAR image segmentation algorithms. In this study, a semantic segmentation algorithm using a cross-regional context and noise regularization (CCNR) for SAR images is proposed. CCNR has three heads to output segmentation results, representation features of each pixel, and reconstructed images. The self-attention and contrastive learning are adopted to explore region-level semantic relations and pixel-level semantic relations between different images, achieving the aggregation of pixels with the same class. Furthermore, to improve the robustness of the network, noise regularization is applied to impose additional constraints on the encoder and segmentation results. The results of experiments conducted on three large scene SAR images prove the efficacy of CCNR. Compared with other comparative algorithms, the proposed CCNR achieves more optimal performance and increased robustness." @default.
- W4379877582 created "2023-06-09" @default.
- W4379877582 creator A5007608227 @default.
- W4379877582 creator A5033300023 @default.
- W4379877582 creator A5036314522 @default.
- W4379877582 creator A5041413561 @default.
- W4379877582 creator A5041938484 @default.
- W4379877582 creator A5043022387 @default.
- W4379877582 creator A5049854957 @default.
- W4379877582 date "2023-07-01" @default.
- W4379877582 modified "2023-10-16" @default.
- W4379877582 title "CCNR: Cross-regional context and noise regularization for SAR image segmentation" @default.
- W4379877582 cites W1903029394 @default.
- W4379877582 cites W1990304459 @default.
- W4379877582 cites W2029235040 @default.
- W4379877582 cites W2085687954 @default.
- W4379877582 cites W2085845644 @default.
- W4379877582 cites W2523566712 @default.
- W4379877582 cites W2560023338 @default.
- W4379877582 cites W2796431263 @default.
- W4379877582 cites W2910628332 @default.
- W4379877582 cites W2964309882 @default.
- W4379877582 cites W2981899103 @default.
- W4379877582 cites W2982220924 @default.
- W4379877582 cites W3010159779 @default.
- W4379877582 cites W3035526186 @default.
- W4379877582 cites W3037578234 @default.
- W4379877582 cites W3110111717 @default.
- W4379877582 cites W3122412340 @default.
- W4379877582 cites W3160032272 @default.
- W4379877582 cites W3170841864 @default.
- W4379877582 cites W3213025198 @default.
- W4379877582 cites W4214893857 @default.
- W4379877582 cites W4283795270 @default.
- W4379877582 doi "https://doi.org/10.1016/j.jag.2023.103363" @default.
- W4379877582 hasPublicationYear "2023" @default.
- W4379877582 type Work @default.
- W4379877582 citedByCount "0" @default.
- W4379877582 crossrefType "journal-article" @default.
- W4379877582 hasAuthorship W4379877582A5007608227 @default.
- W4379877582 hasAuthorship W4379877582A5033300023 @default.
- W4379877582 hasAuthorship W4379877582A5036314522 @default.
- W4379877582 hasAuthorship W4379877582A5041413561 @default.
- W4379877582 hasAuthorship W4379877582A5041938484 @default.
- W4379877582 hasAuthorship W4379877582A5043022387 @default.
- W4379877582 hasAuthorship W4379877582A5049854957 @default.
- W4379877582 hasBestOaLocation W43798775821 @default.
- W4379877582 hasConcept C104317684 @default.
- W4379877582 hasConcept C124504099 @default.
- W4379877582 hasConcept C153180895 @default.
- W4379877582 hasConcept C154945302 @default.
- W4379877582 hasConcept C160633673 @default.
- W4379877582 hasConcept C185592680 @default.
- W4379877582 hasConcept C25694479 @default.
- W4379877582 hasConcept C31972630 @default.
- W4379877582 hasConcept C41008148 @default.
- W4379877582 hasConcept C55493867 @default.
- W4379877582 hasConcept C63479239 @default.
- W4379877582 hasConcept C65885262 @default.
- W4379877582 hasConcept C87360688 @default.
- W4379877582 hasConcept C89600930 @default.
- W4379877582 hasConceptScore W4379877582C104317684 @default.
- W4379877582 hasConceptScore W4379877582C124504099 @default.
- W4379877582 hasConceptScore W4379877582C153180895 @default.
- W4379877582 hasConceptScore W4379877582C154945302 @default.
- W4379877582 hasConceptScore W4379877582C160633673 @default.
- W4379877582 hasConceptScore W4379877582C185592680 @default.
- W4379877582 hasConceptScore W4379877582C25694479 @default.
- W4379877582 hasConceptScore W4379877582C31972630 @default.
- W4379877582 hasConceptScore W4379877582C41008148 @default.
- W4379877582 hasConceptScore W4379877582C55493867 @default.
- W4379877582 hasConceptScore W4379877582C63479239 @default.
- W4379877582 hasConceptScore W4379877582C65885262 @default.
- W4379877582 hasConceptScore W4379877582C87360688 @default.
- W4379877582 hasConceptScore W4379877582C89600930 @default.
- W4379877582 hasLocation W43798775821 @default.
- W4379877582 hasOpenAccess W4379877582 @default.
- W4379877582 hasPrimaryLocation W43798775821 @default.
- W4379877582 hasRelatedWork W1507266234 @default.
- W4379877582 hasRelatedWork W1669643531 @default.
- W4379877582 hasRelatedWork W2069711651 @default.
- W4379877582 hasRelatedWork W2117664411 @default.
- W4379877582 hasRelatedWork W2117933325 @default.
- W4379877582 hasRelatedWork W2549936415 @default.
- W4379877582 hasRelatedWork W2558375057 @default.
- W4379877582 hasRelatedWork W2739874619 @default.
- W4379877582 hasRelatedWork W2897195263 @default.
- W4379877582 hasRelatedWork W1967061043 @default.
- W4379877582 hasVolume "121" @default.
- W4379877582 isParatext "false" @default.
- W4379877582 isRetracted "false" @default.
- W4379877582 workType "article" @default.