Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387301526> ?p ?o ?g. }
- W4387301526 endingPage "173" @default.
- W4387301526 startingPage "155" @default.
- W4387301526 abstract "Recently, in order to pursue better detection results, more convolutional layers and deeper networks are a direction pursued by everyone. However, more and more down-sampling convolution or up-sampling operations generate feature maps of different scales, which makes it difficult to avoid the loss of detailed information of the image, and the distribution of different scales features will be misaligned. In particular, the loss and dislocation of the target boundary information will affect the features learned by the model and reduce the accuracy. This paper proposes a feature alignment method based on non-local idea, and designed two modules—Non Local Align Module (NLA) and Channel Fusion Augment Module (CFA). At the same time, the neighborhood calculation algorithm is also designed for it, which strengthens the binding force on the calculation of boundary information. These two modules can be easily embedded into the current mainstream object detection network to improve the detection effect of the model. Compared to the previous model, the network using our NLA module and CFA module achieves better results than the original model." @default.
- W4387301526 created "2023-10-04" @default.
- W4387301526 creator A5008975323 @default.
- W4387301526 creator A5023315591 @default.
- W4387301526 creator A5025541045 @default.
- W4387301526 creator A5057579407 @default.
- W4387301526 creator A5062646818 @default.
- W4387301526 creator A5075539477 @default.
- W4387301526 creator A5078652354 @default.
- W4387301526 creator A5025961783 @default.
- W4387301526 date "2023-01-01" @default.
- W4387301526 modified "2023-10-04" @default.
- W4387301526 title "NLFA: A Non Local Fusion Alignment Module for Multi-Scale Feature in Object Detection" @default.
- W4387301526 cites W1536680647 @default.
- W4387301526 cites W2037227137 @default.
- W4387301526 cites W2109255472 @default.
- W4387301526 cites W2565639579 @default.
- W4387301526 cites W2570343428 @default.
- W4387301526 cites W2601564443 @default.
- W4387301526 cites W2622826443 @default.
- W4387301526 cites W2752782242 @default.
- W4387301526 cites W2884585870 @default.
- W4387301526 cites W2963037989 @default.
- W4387301526 cites W2963091558 @default.
- W4387301526 cites W2963150697 @default.
- W4387301526 cites W2963179609 @default.
- W4387301526 cites W2963351448 @default.
- W4387301526 cites W2963857746 @default.
- W4387301526 cites W2964241181 @default.
- W4387301526 cites W2965669158 @default.
- W4387301526 cites W2977189914 @default.
- W4387301526 cites W2986357608 @default.
- W4387301526 cites W2986833982 @default.
- W4387301526 cites W3009917598 @default.
- W4387301526 cites W3034475761 @default.
- W4387301526 cites W3042011474 @default.
- W4387301526 cites W3085056143 @default.
- W4387301526 cites W3096609285 @default.
- W4387301526 cites W3106250896 @default.
- W4387301526 cites W3106728613 @default.
- W4387301526 cites W3196107618 @default.
- W4387301526 cites W639708223 @default.
- W4387301526 doi "https://doi.org/10.1007/978-3-031-40070-4_13" @default.
- W4387301526 hasPublicationYear "2023" @default.
- W4387301526 type Work @default.
- W4387301526 citedByCount "0" @default.
- W4387301526 crossrefType "book-chapter" @default.
- W4387301526 hasAuthorship W4387301526A5008975323 @default.
- W4387301526 hasAuthorship W4387301526A5023315591 @default.
- W4387301526 hasAuthorship W4387301526A5025541045 @default.
- W4387301526 hasAuthorship W4387301526A5025961783 @default.
- W4387301526 hasAuthorship W4387301526A5057579407 @default.
- W4387301526 hasAuthorship W4387301526A5062646818 @default.
- W4387301526 hasAuthorship W4387301526A5075539477 @default.
- W4387301526 hasAuthorship W4387301526A5078652354 @default.
- W4387301526 hasConcept C11413529 @default.
- W4387301526 hasConcept C121332964 @default.
- W4387301526 hasConcept C134306372 @default.
- W4387301526 hasConcept C138885662 @default.
- W4387301526 hasConcept C153180895 @default.
- W4387301526 hasConcept C154945302 @default.
- W4387301526 hasConcept C2776151529 @default.
- W4387301526 hasConcept C2776401178 @default.
- W4387301526 hasConcept C2778755073 @default.
- W4387301526 hasConcept C2781238097 @default.
- W4387301526 hasConcept C31972630 @default.
- W4387301526 hasConcept C33923547 @default.
- W4387301526 hasConcept C41008148 @default.
- W4387301526 hasConcept C41895202 @default.
- W4387301526 hasConcept C45347329 @default.
- W4387301526 hasConcept C50644808 @default.
- W4387301526 hasConcept C62354387 @default.
- W4387301526 hasConcept C62520636 @default.
- W4387301526 hasConcept C81363708 @default.
- W4387301526 hasConceptScore W4387301526C11413529 @default.
- W4387301526 hasConceptScore W4387301526C121332964 @default.
- W4387301526 hasConceptScore W4387301526C134306372 @default.
- W4387301526 hasConceptScore W4387301526C138885662 @default.
- W4387301526 hasConceptScore W4387301526C153180895 @default.
- W4387301526 hasConceptScore W4387301526C154945302 @default.
- W4387301526 hasConceptScore W4387301526C2776151529 @default.
- W4387301526 hasConceptScore W4387301526C2776401178 @default.
- W4387301526 hasConceptScore W4387301526C2778755073 @default.
- W4387301526 hasConceptScore W4387301526C2781238097 @default.
- W4387301526 hasConceptScore W4387301526C31972630 @default.
- W4387301526 hasConceptScore W4387301526C33923547 @default.
- W4387301526 hasConceptScore W4387301526C41008148 @default.
- W4387301526 hasConceptScore W4387301526C41895202 @default.
- W4387301526 hasConceptScore W4387301526C45347329 @default.
- W4387301526 hasConceptScore W4387301526C50644808 @default.
- W4387301526 hasConceptScore W4387301526C62354387 @default.
- W4387301526 hasConceptScore W4387301526C62520636 @default.
- W4387301526 hasConceptScore W4387301526C81363708 @default.
- W4387301526 hasLocation W43873015261 @default.
- W4387301526 hasOpenAccess W4387301526 @default.
- W4387301526 hasPrimaryLocation W43873015261 @default.
- W4387301526 hasRelatedWork W1837097281 @default.
- W4387301526 hasRelatedWork W1988485990 @default.