Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386487648> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4386487648 abstract "Camouflage Target Segmentation (COS) aims to segment targets hidden in complex environment. When the existing COS algorithm fuses multi-level features, it ignores the expression and positioning of the edge features of the camouflage target, and pays more attention to the influence of the fusion of features on the segmentation performance. Therefore, a COS algorithm based on disguised target segmentation based on reverse attention and self-interaction fusion is proposed. First, multi-scale features are extracted through the backbone network; Then, in order to improve the expression ability of edge features, the features extracted by the backbone network are enhanced using a network composed of a reverse attention module (RAM); Finally, the self-interaction fusion module (SIM) drives the features of different scales to achieve layer-by-layer fusion, while suppressing noise interference and obtaining more accurate target information. Experimental results show that on the three commonly used natural camouflage datasets of CHAMELEON, CAMO and CODIOK, the model shows better segmentation effect than other typical models." @default.
- W4386487648 created "2023-09-07" @default.
- W4386487648 creator A5001077766 @default.
- W4386487648 creator A5006489912 @default.
- W4386487648 creator A5019287409 @default.
- W4386487648 creator A5022885900 @default.
- W4386487648 creator A5032648109 @default.
- W4386487648 creator A5033213528 @default.
- W4386487648 date "2023-03-01" @default.
- W4386487648 modified "2023-09-29" @default.
- W4386487648 title "Camouflage target segmentation based on reverse attention and self-interaction fusion" @default.
- W4386487648 cites W2796975587 @default.
- W4386487648 cites W2928165649 @default.
- W4386487648 cites W2943545929 @default.
- W4386487648 cites W2948510860 @default.
- W4386487648 cites W2962914239 @default.
- W4386487648 cites W2962948774 @default.
- W4386487648 cites W2963112696 @default.
- W4386487648 cites W2963420686 @default.
- W4386487648 cites W2963529609 @default.
- W4386487648 cites W2990984982 @default.
- W4386487648 cites W2997316506 @default.
- W4386487648 cites W3035422681 @default.
- W4386487648 cites W3092344722 @default.
- W4386487648 cites W3210073375 @default.
- W4386487648 doi "https://doi.org/10.1109/icnlp58431.2023.00015" @default.
- W4386487648 hasPublicationYear "2023" @default.
- W4386487648 type Work @default.
- W4386487648 citedByCount "0" @default.
- W4386487648 crossrefType "proceedings-article" @default.
- W4386487648 hasAuthorship W4386487648A5001077766 @default.
- W4386487648 hasAuthorship W4386487648A5006489912 @default.
- W4386487648 hasAuthorship W4386487648A5019287409 @default.
- W4386487648 hasAuthorship W4386487648A5022885900 @default.
- W4386487648 hasAuthorship W4386487648A5032648109 @default.
- W4386487648 hasAuthorship W4386487648A5033213528 @default.
- W4386487648 hasConcept C115961682 @default.
- W4386487648 hasConcept C124504099 @default.
- W4386487648 hasConcept C127162648 @default.
- W4386487648 hasConcept C138885662 @default.
- W4386487648 hasConcept C153180895 @default.
- W4386487648 hasConcept C154945302 @default.
- W4386487648 hasConcept C158525013 @default.
- W4386487648 hasConcept C162307627 @default.
- W4386487648 hasConcept C2776196576 @default.
- W4386487648 hasConcept C31972630 @default.
- W4386487648 hasConcept C32022120 @default.
- W4386487648 hasConcept C41008148 @default.
- W4386487648 hasConcept C41895202 @default.
- W4386487648 hasConcept C76155785 @default.
- W4386487648 hasConcept C89600930 @default.
- W4386487648 hasConcept C99498987 @default.
- W4386487648 hasConceptScore W4386487648C115961682 @default.
- W4386487648 hasConceptScore W4386487648C124504099 @default.
- W4386487648 hasConceptScore W4386487648C127162648 @default.
- W4386487648 hasConceptScore W4386487648C138885662 @default.
- W4386487648 hasConceptScore W4386487648C153180895 @default.
- W4386487648 hasConceptScore W4386487648C154945302 @default.
- W4386487648 hasConceptScore W4386487648C158525013 @default.
- W4386487648 hasConceptScore W4386487648C162307627 @default.
- W4386487648 hasConceptScore W4386487648C2776196576 @default.
- W4386487648 hasConceptScore W4386487648C31972630 @default.
- W4386487648 hasConceptScore W4386487648C32022120 @default.
- W4386487648 hasConceptScore W4386487648C41008148 @default.
- W4386487648 hasConceptScore W4386487648C41895202 @default.
- W4386487648 hasConceptScore W4386487648C76155785 @default.
- W4386487648 hasConceptScore W4386487648C89600930 @default.
- W4386487648 hasConceptScore W4386487648C99498987 @default.
- W4386487648 hasLocation W43864876481 @default.
- W4386487648 hasOpenAccess W4386487648 @default.
- W4386487648 hasPrimaryLocation W43864876481 @default.
- W4386487648 hasRelatedWork W1669643531 @default.
- W4386487648 hasRelatedWork W1982826852 @default.
- W4386487648 hasRelatedWork W2005437358 @default.
- W4386487648 hasRelatedWork W2008656436 @default.
- W4386487648 hasRelatedWork W2023558673 @default.
- W4386487648 hasRelatedWork W2110230079 @default.
- W4386487648 hasRelatedWork W2134924024 @default.
- W4386487648 hasRelatedWork W2517104666 @default.
- W4386487648 hasRelatedWork W2613186388 @default.
- W4386487648 hasRelatedWork W1967061043 @default.
- W4386487648 isParatext "false" @default.
- W4386487648 isRetracted "false" @default.
- W4386487648 workType "article" @default.