Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361861910> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4361861910 abstract "Obstacle detection using semantic segmentation shows a great promise for unmanned surface vehicles(USVs) in unstable marine environments. Unlike traditional machine learning, semantic segmentation models need to define suitable backbones in advance to extract features of key pixels. However, although the variety and number of backbones are massive, choosing the best one for the developer's environment in the practical application can be a daunting task. Past researches attempt to explore the ranking of backbones in specific scenarios by retraining all mainstream backbone models, which has a certain effect on some single and unchanged land scenes, but cannot be adapted to the unstable marine environment. Therefore, this paper proposes a method to quickly evaluate the suitable backbone, by extracting the representation models of different backbones without retraining and fine-tuning, separating the super-pixels of their feature distribution maps, comparing the features of different models according to likelihood distribution,and finally providing corresponding evaluation scores to give reference for backbone selection. Experimental results show that the proposed approach can provide precise backbone evaluation scores without increasing the computational effort, which can help developers quickly and accurately select the best backbone suitable for their own environment, and further design more accurate semantic segmentation models for unmanned surface vehicles." @default.
- W4361861910 created "2023-04-05" @default.
- W4361861910 creator A5004632623 @default.
- W4361861910 creator A5017795751 @default.
- W4361861910 creator A5030863883 @default.
- W4361861910 creator A5081273424 @default.
- W4361861910 date "2022-12-01" @default.
- W4361861910 modified "2023-09-28" @default.
- W4361861910 title "Efficient Semantic Segmentation Backbone Evaluation for Unmanned Surface Vehicles based on Likelihood Distribution Estimation" @default.
- W4361861910 cites W2034938692 @default.
- W4361861910 cites W2044328399 @default.
- W4361861910 cites W2115157385 @default.
- W4361861910 cites W2119531662 @default.
- W4361861910 cites W2127369486 @default.
- W4361861910 cites W2143668817 @default.
- W4361861910 cites W2157929363 @default.
- W4361861910 cites W2160754664 @default.
- W4361861910 cites W2460157116 @default.
- W4361861910 cites W2509467614 @default.
- W4361861910 cites W2552331162 @default.
- W4361861910 cites W2560023338 @default.
- W4361861910 cites W2761406764 @default.
- W4361861910 cites W2787889241 @default.
- W4361861910 cites W3003522438 @default.
- W4361861910 cites W3090912915 @default.
- W4361861910 cites W3186318472 @default.
- W4361861910 cites W4226251159 @default.
- W4361861910 cites W4288083803 @default.
- W4361861910 doi "https://doi.org/10.1109/msn57253.2022.00076" @default.
- W4361861910 hasPublicationYear "2022" @default.
- W4361861910 type Work @default.
- W4361861910 citedByCount "0" @default.
- W4361861910 crossrefType "proceedings-article" @default.
- W4361861910 hasAuthorship W4361861910A5004632623 @default.
- W4361861910 hasAuthorship W4361861910A5017795751 @default.
- W4361861910 hasAuthorship W4361861910A5030863883 @default.
- W4361861910 hasAuthorship W4361861910A5081273424 @default.
- W4361861910 hasConcept C119857082 @default.
- W4361861910 hasConcept C138885662 @default.
- W4361861910 hasConcept C153180895 @default.
- W4361861910 hasConcept C154945302 @default.
- W4361861910 hasConcept C162324750 @default.
- W4361861910 hasConcept C17744445 @default.
- W4361861910 hasConcept C187736073 @default.
- W4361861910 hasConcept C189430467 @default.
- W4361861910 hasConcept C199539241 @default.
- W4361861910 hasConcept C2776359362 @default.
- W4361861910 hasConcept C2776401178 @default.
- W4361861910 hasConcept C2776650193 @default.
- W4361861910 hasConcept C2780451532 @default.
- W4361861910 hasConcept C31258907 @default.
- W4361861910 hasConcept C31972630 @default.
- W4361861910 hasConcept C41008148 @default.
- W4361861910 hasConcept C41895202 @default.
- W4361861910 hasConcept C88796919 @default.
- W4361861910 hasConcept C89600930 @default.
- W4361861910 hasConcept C94625758 @default.
- W4361861910 hasConceptScore W4361861910C119857082 @default.
- W4361861910 hasConceptScore W4361861910C138885662 @default.
- W4361861910 hasConceptScore W4361861910C153180895 @default.
- W4361861910 hasConceptScore W4361861910C154945302 @default.
- W4361861910 hasConceptScore W4361861910C162324750 @default.
- W4361861910 hasConceptScore W4361861910C17744445 @default.
- W4361861910 hasConceptScore W4361861910C187736073 @default.
- W4361861910 hasConceptScore W4361861910C189430467 @default.
- W4361861910 hasConceptScore W4361861910C199539241 @default.
- W4361861910 hasConceptScore W4361861910C2776359362 @default.
- W4361861910 hasConceptScore W4361861910C2776401178 @default.
- W4361861910 hasConceptScore W4361861910C2776650193 @default.
- W4361861910 hasConceptScore W4361861910C2780451532 @default.
- W4361861910 hasConceptScore W4361861910C31258907 @default.
- W4361861910 hasConceptScore W4361861910C31972630 @default.
- W4361861910 hasConceptScore W4361861910C41008148 @default.
- W4361861910 hasConceptScore W4361861910C41895202 @default.
- W4361861910 hasConceptScore W4361861910C88796919 @default.
- W4361861910 hasConceptScore W4361861910C89600930 @default.
- W4361861910 hasConceptScore W4361861910C94625758 @default.
- W4361861910 hasFunder F4320335787 @default.
- W4361861910 hasLocation W43618619101 @default.
- W4361861910 hasOpenAccess W4361861910 @default.
- W4361861910 hasPrimaryLocation W43618619101 @default.
- W4361861910 hasRelatedWork W1605248340 @default.
- W4361861910 hasRelatedWork W1605906521 @default.
- W4361861910 hasRelatedWork W2008348169 @default.
- W4361861910 hasRelatedWork W2045615376 @default.
- W4361861910 hasRelatedWork W2051516969 @default.
- W4361861910 hasRelatedWork W2126807813 @default.
- W4361861910 hasRelatedWork W2134731391 @default.
- W4361861910 hasRelatedWork W2166492906 @default.
- W4361861910 hasRelatedWork W2242126349 @default.
- W4361861910 hasRelatedWork W4293799789 @default.
- W4361861910 isParatext "false" @default.
- W4361861910 isRetracted "false" @default.
- W4361861910 workType "article" @default.