Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367016311> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4367016311 abstract "Instance segmentation is a new method in the field of security monitoring. The current models perform well in sufficient light. However, in the actual environment, due to the change of light in the scene, the picture will randomly appear with high noise, low brightness and other problems which seriously affect the segmentation accuracy. Therefore, two S-BCNet based on BCNet are proposed in this paper, which respectively achieve better performance under complex light and constant dim-light conditions. In order to improve the generalization, we propose a new Shrinkage Module based on a soft thresholding function and insert it into BCNet's backbone so that it can learn and filter noise autonomously. Moreover, we propose a dim-light processing method and produce two datasets: COCO-D(dark light) and COCO-M(complex light) based on COCO, which are specifically used to train and test the performance of the mode in various degrees of dim-light environments. Furthermore, we use AdaBN to improve our S-BCNet and use the COCO-D for transfer learning to train the model for dark-light specialization, specifically for use in constant dim-light scenes. Experiments show that our models improve by 10.7% and 17.2% respectively compared with the best mainstream model in the two environments." @default.
- W4367016311 created "2023-04-27" @default.
- W4367016311 creator A5024793526 @default.
- W4367016311 creator A5029337636 @default.
- W4367016311 creator A5039638672 @default.
- W4367016311 creator A5050281178 @default.
- W4367016311 creator A5058339130 @default.
- W4367016311 date "2023-02-24" @default.
- W4367016311 modified "2023-09-28" @default.
- W4367016311 title "Dim-Light Instance Segmentation Based on Soft Thresholding and Improved BCNet" @default.
- W4367016311 cites W2194775991 @default.
- W4367016311 cites W2565639579 @default.
- W4367016311 cites W2920326761 @default.
- W4367016311 cites W2963150697 @default.
- W4367016311 cites W2963857746 @default.
- W4367016311 cites W2977117446 @default.
- W4367016311 cites W2982770724 @default.
- W4367016311 cites W2993182889 @default.
- W4367016311 cites W3035358681 @default.
- W4367016311 cites W3113410735 @default.
- W4367016311 cites W3165113810 @default.
- W4367016311 cites W3167260844 @default.
- W4367016311 cites W4290671759 @default.
- W4367016311 cites W4292787479 @default.
- W4367016311 doi "https://doi.org/10.1109/nnice58320.2023.10105765" @default.
- W4367016311 hasPublicationYear "2023" @default.
- W4367016311 type Work @default.
- W4367016311 citedByCount "0" @default.
- W4367016311 crossrefType "proceedings-article" @default.
- W4367016311 hasAuthorship W4367016311A5024793526 @default.
- W4367016311 hasAuthorship W4367016311A5029337636 @default.
- W4367016311 hasAuthorship W4367016311A5039638672 @default.
- W4367016311 hasAuthorship W4367016311A5050281178 @default.
- W4367016311 hasAuthorship W4367016311A5058339130 @default.
- W4367016311 hasConcept C106131492 @default.
- W4367016311 hasConcept C115961682 @default.
- W4367016311 hasConcept C120665830 @default.
- W4367016311 hasConcept C121332964 @default.
- W4367016311 hasConcept C125245961 @default.
- W4367016311 hasConcept C134306372 @default.
- W4367016311 hasConcept C153180895 @default.
- W4367016311 hasConcept C154945302 @default.
- W4367016311 hasConcept C177148314 @default.
- W4367016311 hasConcept C191178318 @default.
- W4367016311 hasConcept C31972630 @default.
- W4367016311 hasConcept C33923547 @default.
- W4367016311 hasConcept C41008148 @default.
- W4367016311 hasConcept C48983235 @default.
- W4367016311 hasConcept C89600930 @default.
- W4367016311 hasConcept C99498987 @default.
- W4367016311 hasConceptScore W4367016311C106131492 @default.
- W4367016311 hasConceptScore W4367016311C115961682 @default.
- W4367016311 hasConceptScore W4367016311C120665830 @default.
- W4367016311 hasConceptScore W4367016311C121332964 @default.
- W4367016311 hasConceptScore W4367016311C125245961 @default.
- W4367016311 hasConceptScore W4367016311C134306372 @default.
- W4367016311 hasConceptScore W4367016311C153180895 @default.
- W4367016311 hasConceptScore W4367016311C154945302 @default.
- W4367016311 hasConceptScore W4367016311C177148314 @default.
- W4367016311 hasConceptScore W4367016311C191178318 @default.
- W4367016311 hasConceptScore W4367016311C31972630 @default.
- W4367016311 hasConceptScore W4367016311C33923547 @default.
- W4367016311 hasConceptScore W4367016311C41008148 @default.
- W4367016311 hasConceptScore W4367016311C48983235 @default.
- W4367016311 hasConceptScore W4367016311C89600930 @default.
- W4367016311 hasConceptScore W4367016311C99498987 @default.
- W4367016311 hasLocation W43670163111 @default.
- W4367016311 hasOpenAccess W4367016311 @default.
- W4367016311 hasPrimaryLocation W43670163111 @default.
- W4367016311 hasRelatedWork W1509621893 @default.
- W4367016311 hasRelatedWork W1669643531 @default.
- W4367016311 hasRelatedWork W2008656436 @default.
- W4367016311 hasRelatedWork W2027450165 @default.
- W4367016311 hasRelatedWork W2039154422 @default.
- W4367016311 hasRelatedWork W2058443653 @default.
- W4367016311 hasRelatedWork W2134924024 @default.
- W4367016311 hasRelatedWork W2347731544 @default.
- W4367016311 hasRelatedWork W2411367154 @default.
- W4367016311 hasRelatedWork W2517104666 @default.
- W4367016311 isParatext "false" @default.
- W4367016311 isRetracted "false" @default.
- W4367016311 workType "article" @default.