Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292388149> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4292388149 abstract "Object detection in remote sensing images has be-come a research focus in recent years with the development of deep learning. However, due to objective reasons such as weather, cost, etc., we can hardly obtain abundant high-quality remote sensing images, especially for specific targets, which severely limits the training of the object detector, leading to poor detection performance. Thus for the first time, this paper introduces the Generative Adversarial Networks(GANs) for arbitrary-oriented object detection in remote sensing images, by augmenting the dataset to improve the performance of detectors. We construct DETGAN with two-layer self-attention modules to capture long-distance dependence for high-quality image generation. To solve the mismatch between generated slices and the samples for detectors, we propose the GAN-to-Detection transfer strategy, in which the slices are inserted into a background with the same size as the samples for detectors and then added to the training set. Experiments show that the performance of ship detectors is successfully improved with the transfer strategy, and demonstrate that GAN is an effective way to alleviate the problem of data insufficiency in remote sensing image object detection." @default.
- W4292388149 created "2022-08-20" @default.
- W4292388149 creator A5019797064 @default.
- W4292388149 creator A5025485353 @default.
- W4292388149 creator A5025955594 @default.
- W4292388149 creator A5055332125 @default.
- W4292388149 date "2022-03-01" @default.
- W4292388149 modified "2023-09-26" @default.
- W4292388149 title "DETGAN: GAN for Arbitrary-oriented Object Detection in Remote Sensing Images" @default.
- W4292388149 cites W1975517671 @default.
- W4292388149 cites W2535388113 @default.
- W4292388149 cites W2762941833 @default.
- W4292388149 cites W2890833618 @default.
- W4292388149 cites W2931068004 @default.
- W4292388149 cites W2991359031 @default.
- W4292388149 cites W2997085028 @default.
- W4292388149 cites W3036479037 @default.
- W4292388149 cites W3105577662 @default.
- W4292388149 cites W3163345304 @default.
- W4292388149 doi "https://doi.org/10.1109/cacml55074.2022.00063" @default.
- W4292388149 hasPublicationYear "2022" @default.
- W4292388149 type Work @default.
- W4292388149 citedByCount "0" @default.
- W4292388149 crossrefType "proceedings-article" @default.
- W4292388149 hasAuthorship W4292388149A5019797064 @default.
- W4292388149 hasAuthorship W4292388149A5025485353 @default.
- W4292388149 hasAuthorship W4292388149A5025955594 @default.
- W4292388149 hasAuthorship W4292388149A5055332125 @default.
- W4292388149 hasConcept C111472728 @default.
- W4292388149 hasConcept C120665830 @default.
- W4292388149 hasConcept C121332964 @default.
- W4292388149 hasConcept C138885662 @default.
- W4292388149 hasConcept C153180895 @default.
- W4292388149 hasConcept C154945302 @default.
- W4292388149 hasConcept C177264268 @default.
- W4292388149 hasConcept C192209626 @default.
- W4292388149 hasConcept C199360897 @default.
- W4292388149 hasConcept C205649164 @default.
- W4292388149 hasConcept C2776151529 @default.
- W4292388149 hasConcept C2779530757 @default.
- W4292388149 hasConcept C2781238097 @default.
- W4292388149 hasConcept C31972630 @default.
- W4292388149 hasConcept C41008148 @default.
- W4292388149 hasConcept C62649853 @default.
- W4292388149 hasConcept C76155785 @default.
- W4292388149 hasConcept C94915269 @default.
- W4292388149 hasConceptScore W4292388149C111472728 @default.
- W4292388149 hasConceptScore W4292388149C120665830 @default.
- W4292388149 hasConceptScore W4292388149C121332964 @default.
- W4292388149 hasConceptScore W4292388149C138885662 @default.
- W4292388149 hasConceptScore W4292388149C153180895 @default.
- W4292388149 hasConceptScore W4292388149C154945302 @default.
- W4292388149 hasConceptScore W4292388149C177264268 @default.
- W4292388149 hasConceptScore W4292388149C192209626 @default.
- W4292388149 hasConceptScore W4292388149C199360897 @default.
- W4292388149 hasConceptScore W4292388149C205649164 @default.
- W4292388149 hasConceptScore W4292388149C2776151529 @default.
- W4292388149 hasConceptScore W4292388149C2779530757 @default.
- W4292388149 hasConceptScore W4292388149C2781238097 @default.
- W4292388149 hasConceptScore W4292388149C31972630 @default.
- W4292388149 hasConceptScore W4292388149C41008148 @default.
- W4292388149 hasConceptScore W4292388149C62649853 @default.
- W4292388149 hasConceptScore W4292388149C76155785 @default.
- W4292388149 hasConceptScore W4292388149C94915269 @default.
- W4292388149 hasLocation W42923881491 @default.
- W4292388149 hasOpenAccess W4292388149 @default.
- W4292388149 hasPrimaryLocation W42923881491 @default.
- W4292388149 hasRelatedWork W1971759388 @default.
- W4292388149 hasRelatedWork W2004370856 @default.
- W4292388149 hasRelatedWork W2007544051 @default.
- W4292388149 hasRelatedWork W2021186063 @default.
- W4292388149 hasRelatedWork W2025800131 @default.
- W4292388149 hasRelatedWork W2028264897 @default.
- W4292388149 hasRelatedWork W2095705906 @default.
- W4292388149 hasRelatedWork W2129974284 @default.
- W4292388149 hasRelatedWork W2520844843 @default.
- W4292388149 hasRelatedWork W2975200075 @default.
- W4292388149 isParatext "false" @default.
- W4292388149 isRetracted "false" @default.
- W4292388149 workType "article" @default.