Matches in SemOpenAlex for { <https://semopenalex.org/work/W3011101372> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3011101372 abstract "Accurate detection of ship targets is a research hotspot in computer vision. Most of the researches have achieved instance-level detection in the way of bounding box. But we intend to achieve more accurate detection of ship targets in pixel-level through semantic segmentation. However, there are still two main challenges: the first one is the difficulty to segment small targets caused by the difference among ship targets' scales, and the other one is the lack of localization information caused by insufficient recovery ability of the decoder part. In this paper, we propose an effective solution. First, a multi-scale pooling fusion module is proposed to fuse multi-scale feature maps and acquire more multi-scale context information, then we improve the capability of precise decoding by taking the place of convolution operation with deconvolution in the decoder part to gather more localization information. At last, we integrate above two schemes into an encoder-decoder symmetry training network with less training parameters and less training time. Furthermore, we construct a dataset for ship semantic segmentation called HRSC2016-SS by labeling HRSC2016 dataset to evaluate our solution. Experiments show that comparing with the existing methods, our proposed solution has a better performance." @default.
- W3011101372 created "2020-03-23" @default.
- W3011101372 creator A5007396281 @default.
- W3011101372 creator A5032383728 @default.
- W3011101372 creator A5048850333 @default.
- W3011101372 creator A5052968920 @default.
- W3011101372 creator A5059004995 @default.
- W3011101372 creator A5062247330 @default.
- W3011101372 date "2019-07-01" @default.
- W3011101372 modified "2023-09-23" @default.
- W3011101372 title "A New Network Structure for Semantic Segmentation of Ship Targets in Remote Sensing" @default.
- W3011101372 cites W1745334888 @default.
- W3011101372 cites W1977792424 @default.
- W3011101372 cites W2021320781 @default.
- W3011101372 cites W2025183033 @default.
- W3011101372 cites W2090518410 @default.
- W3011101372 cites W2097117768 @default.
- W3011101372 cites W2109255472 @default.
- W3011101372 cites W2110764733 @default.
- W3011101372 cites W2141200610 @default.
- W3011101372 cites W2293724088 @default.
- W3011101372 cites W2400138547 @default.
- W3011101372 cites W2412782625 @default.
- W3011101372 cites W2442495293 @default.
- W3011101372 cites W2538403209 @default.
- W3011101372 cites W2555441839 @default.
- W3011101372 cites W2562706821 @default.
- W3011101372 cites W2594177559 @default.
- W3011101372 cites W2618530766 @default.
- W3011101372 cites W2919115771 @default.
- W3011101372 cites W4243570436 @default.
- W3011101372 doi "https://doi.org/10.23919/fusion43075.2019.9011331" @default.
- W3011101372 hasPublicationYear "2019" @default.
- W3011101372 type Work @default.
- W3011101372 sameAs 3011101372 @default.
- W3011101372 citedByCount "0" @default.
- W3011101372 crossrefType "proceedings-article" @default.
- W3011101372 hasAuthorship W3011101372A5007396281 @default.
- W3011101372 hasAuthorship W3011101372A5032383728 @default.
- W3011101372 hasAuthorship W3011101372A5048850333 @default.
- W3011101372 hasAuthorship W3011101372A5052968920 @default.
- W3011101372 hasAuthorship W3011101372A5059004995 @default.
- W3011101372 hasAuthorship W3011101372A5062247330 @default.
- W3011101372 hasConcept C11413529 @default.
- W3011101372 hasConcept C115961682 @default.
- W3011101372 hasConcept C124504099 @default.
- W3011101372 hasConcept C147037132 @default.
- W3011101372 hasConcept C153180895 @default.
- W3011101372 hasConcept C154945302 @default.
- W3011101372 hasConcept C160633673 @default.
- W3011101372 hasConcept C174576160 @default.
- W3011101372 hasConcept C31972630 @default.
- W3011101372 hasConcept C41008148 @default.
- W3011101372 hasConcept C45347329 @default.
- W3011101372 hasConcept C50644808 @default.
- W3011101372 hasConcept C57273362 @default.
- W3011101372 hasConcept C70437156 @default.
- W3011101372 hasConcept C89600930 @default.
- W3011101372 hasConceptScore W3011101372C11413529 @default.
- W3011101372 hasConceptScore W3011101372C115961682 @default.
- W3011101372 hasConceptScore W3011101372C124504099 @default.
- W3011101372 hasConceptScore W3011101372C147037132 @default.
- W3011101372 hasConceptScore W3011101372C153180895 @default.
- W3011101372 hasConceptScore W3011101372C154945302 @default.
- W3011101372 hasConceptScore W3011101372C160633673 @default.
- W3011101372 hasConceptScore W3011101372C174576160 @default.
- W3011101372 hasConceptScore W3011101372C31972630 @default.
- W3011101372 hasConceptScore W3011101372C41008148 @default.
- W3011101372 hasConceptScore W3011101372C45347329 @default.
- W3011101372 hasConceptScore W3011101372C50644808 @default.
- W3011101372 hasConceptScore W3011101372C57273362 @default.
- W3011101372 hasConceptScore W3011101372C70437156 @default.
- W3011101372 hasConceptScore W3011101372C89600930 @default.
- W3011101372 hasLocation W30111013721 @default.
- W3011101372 hasOpenAccess W3011101372 @default.
- W3011101372 hasPrimaryLocation W30111013721 @default.
- W3011101372 hasRelatedWork W1669643531 @default.
- W3011101372 hasRelatedWork W2027450165 @default.
- W3011101372 hasRelatedWork W2039154422 @default.
- W3011101372 hasRelatedWork W2049569768 @default.
- W3011101372 hasRelatedWork W2090093270 @default.
- W3011101372 hasRelatedWork W2517104666 @default.
- W3011101372 hasRelatedWork W2895616727 @default.
- W3011101372 hasRelatedWork W2895946091 @default.
- W3011101372 hasRelatedWork W3024944150 @default.
- W3011101372 hasRelatedWork W3046352749 @default.
- W3011101372 isParatext "false" @default.
- W3011101372 isRetracted "false" @default.
- W3011101372 magId "3011101372" @default.
- W3011101372 workType "article" @default.