Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226088892> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4226088892 endingPage "9230" @default.
- W4226088892 startingPage "9220" @default.
- W4226088892 abstract "In this paper, we propose a novel generative framework which uses Generative Adversarial Networks (GANs) to generate features that provide robustness for object detection on reduced-quality images. The proposed GAN-based Detection of Objects (GAN-DO) framework is not restricted to any particular architecture and can be generalized to several deep neural network (DNN) based architectures. The resulting deep neural network maintains the exact architecture as the selected baseline model without adding to the model parameter complexity or inference speed. We first evaluate the effect of image quality on both object classification and object bounding box regression. We then test the models resulting from our proposed GAN-DO framework, using two state-of-the-art object detection architectures as the baseline models. We also evaluate the effect of the number of re-trained parameters in the generator of GAN-DO on the accuracy of the final trained model. Performance results provided using GAN-DO on object detection datasets establish an improved robustness to varying image quality and a higher mAP compared to the existing approaches." @default.
- W4226088892 created "2022-05-05" @default.
- W4226088892 creator A5015809828 @default.
- W4226088892 creator A5036218196 @default.
- W4226088892 date "2021-01-01" @default.
- W4226088892 modified "2023-10-11" @default.
- W4226088892 title "It GAN Do Better: GAN-Based Detection of Objects on Images With Varying Quality" @default.
- W4226088892 cites W1978749115 @default.
- W4226088892 cites W2031489346 @default.
- W4226088892 cites W2097117768 @default.
- W4226088892 cites W2117539524 @default.
- W4226088892 cites W2194775991 @default.
- W4226088892 cites W2300657047 @default.
- W4226088892 cites W2342045095 @default.
- W4226088892 cites W2565639579 @default.
- W4226088892 cites W2625219738 @default.
- W4226088892 cites W2777194773 @default.
- W4226088892 cites W2798412221 @default.
- W4226088892 cites W2798748382 @default.
- W4226088892 cites W2884561390 @default.
- W4226088892 cites W2887876256 @default.
- W4226088892 cites W2896155169 @default.
- W4226088892 cites W2963073614 @default.
- W4226088892 cites W2963312584 @default.
- W4226088892 cites W2963420272 @default.
- W4226088892 cites W2963669006 @default.
- W4226088892 cites W2963980515 @default.
- W4226088892 cites W2981705647 @default.
- W4226088892 cites W3102278250 @default.
- W4226088892 cites W3104668471 @default.
- W4226088892 cites W639708223 @default.
- W4226088892 doi "https://doi.org/10.1109/tip.2021.3124155" @default.
- W4226088892 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34735343" @default.
- W4226088892 hasPublicationYear "2021" @default.
- W4226088892 type Work @default.
- W4226088892 citedByCount "14" @default.
- W4226088892 countsByYear W42260888922022 @default.
- W4226088892 countsByYear W42260888922023 @default.
- W4226088892 crossrefType "journal-article" @default.
- W4226088892 hasAuthorship W4226088892A5015809828 @default.
- W4226088892 hasAuthorship W4226088892A5036218196 @default.
- W4226088892 hasBestOaLocation W42260888922 @default.
- W4226088892 hasConcept C104317684 @default.
- W4226088892 hasConcept C115961682 @default.
- W4226088892 hasConcept C147037132 @default.
- W4226088892 hasConcept C153180895 @default.
- W4226088892 hasConcept C154945302 @default.
- W4226088892 hasConcept C185592680 @default.
- W4226088892 hasConcept C2776151529 @default.
- W4226088892 hasConcept C2776214188 @default.
- W4226088892 hasConcept C31972630 @default.
- W4226088892 hasConcept C41008148 @default.
- W4226088892 hasConcept C50644808 @default.
- W4226088892 hasConcept C55020928 @default.
- W4226088892 hasConcept C55493867 @default.
- W4226088892 hasConcept C63479239 @default.
- W4226088892 hasConceptScore W4226088892C104317684 @default.
- W4226088892 hasConceptScore W4226088892C115961682 @default.
- W4226088892 hasConceptScore W4226088892C147037132 @default.
- W4226088892 hasConceptScore W4226088892C153180895 @default.
- W4226088892 hasConceptScore W4226088892C154945302 @default.
- W4226088892 hasConceptScore W4226088892C185592680 @default.
- W4226088892 hasConceptScore W4226088892C2776151529 @default.
- W4226088892 hasConceptScore W4226088892C2776214188 @default.
- W4226088892 hasConceptScore W4226088892C31972630 @default.
- W4226088892 hasConceptScore W4226088892C41008148 @default.
- W4226088892 hasConceptScore W4226088892C50644808 @default.
- W4226088892 hasConceptScore W4226088892C55020928 @default.
- W4226088892 hasConceptScore W4226088892C55493867 @default.
- W4226088892 hasConceptScore W4226088892C63479239 @default.
- W4226088892 hasLocation W42260888921 @default.
- W4226088892 hasLocation W42260888922 @default.
- W4226088892 hasLocation W42260888923 @default.
- W4226088892 hasLocation W42260888924 @default.
- W4226088892 hasOpenAccess W4226088892 @default.
- W4226088892 hasPrimaryLocation W42260888921 @default.
- W4226088892 hasRelatedWork W2035976912 @default.
- W4226088892 hasRelatedWork W2541791370 @default.
- W4226088892 hasRelatedWork W2766547489 @default.
- W4226088892 hasRelatedWork W2782964878 @default.
- W4226088892 hasRelatedWork W2921707373 @default.
- W4226088892 hasRelatedWork W2922421953 @default.
- W4226088892 hasRelatedWork W3002270006 @default.
- W4226088892 hasRelatedWork W3015973434 @default.
- W4226088892 hasRelatedWork W3094187672 @default.
- W4226088892 hasRelatedWork W3211653591 @default.
- W4226088892 hasVolume "30" @default.
- W4226088892 isParatext "false" @default.
- W4226088892 isRetracted "false" @default.
- W4226088892 workType "article" @default.