Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205111034> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3205111034 abstract "Understanding the notion of normality in visual data is a complex issue in computer vision with plenty of potential applications in several sectors. The immense effort required for optimal design for real-world application of existing methods warrants the need for a generic framework that is efficient, automated and can be momentarily deployed for the operation, reducing the effort expended on model design and hyper-parameter tuning. Hence, we propose a novel, modular and model-agnostic improvement to the conventional AutoEncoder architecture, based on visual soft-attention for the inputs to make them robust and readily improve their performance in automated semi-supervised visual anomaly detection tasks, without any extra effort in terms of hyperparameter tuning. Besides, we discuss the role of attention in AutoEncoders (AE) that can significantly improve learning and the efficacy of the models with detailed experimental results on diverse visual anomaly detection datasets." @default.
- W3205111034 created "2021-10-25" @default.
- W3205111034 creator A5001202312 @default.
- W3205111034 creator A5070046659 @default.
- W3205111034 date "2021-08-11" @default.
- W3205111034 modified "2023-10-14" @default.
- W3205111034 title "Attentive Autoencoders For Improving Visual Anomaly Detection" @default.
- W3205111034 cites W2110798204 @default.
- W3205111034 cites W2122361470 @default.
- W3205111034 cites W2122646361 @default.
- W3205111034 cites W2163612318 @default.
- W3205111034 cites W2164261375 @default.
- W3205111034 cites W2172806452 @default.
- W3205111034 cites W2179488730 @default.
- W3205111034 cites W2341058432 @default.
- W3205111034 cites W2550553598 @default.
- W3205111034 cites W2613833277 @default.
- W3205111034 cites W2739846485 @default.
- W3205111034 cites W2787420051 @default.
- W3205111034 cites W2810818658 @default.
- W3205111034 cites W2910068345 @default.
- W3205111034 cites W2951527505 @default.
- W3205111034 cites W2963046013 @default.
- W3205111034 cites W2963091558 @default.
- W3205111034 cites W2963420686 @default.
- W3205111034 cites W2964308564 @default.
- W3205111034 cites W2981413347 @default.
- W3205111034 cites W3102785203 @default.
- W3205111034 cites W3112221804 @default.
- W3205111034 doi "https://doi.org/10.1109/icas49788.2021.9551183" @default.
- W3205111034 hasPublicationYear "2021" @default.
- W3205111034 type Work @default.
- W3205111034 sameAs 3205111034 @default.
- W3205111034 citedByCount "0" @default.
- W3205111034 crossrefType "proceedings-article" @default.
- W3205111034 hasAuthorship W3205111034A5001202312 @default.
- W3205111034 hasAuthorship W3205111034A5070046659 @default.
- W3205111034 hasConcept C101468663 @default.
- W3205111034 hasConcept C101738243 @default.
- W3205111034 hasConcept C108583219 @default.
- W3205111034 hasConcept C111919701 @default.
- W3205111034 hasConcept C119857082 @default.
- W3205111034 hasConcept C153180895 @default.
- W3205111034 hasConcept C154945302 @default.
- W3205111034 hasConcept C36464697 @default.
- W3205111034 hasConcept C41008148 @default.
- W3205111034 hasConcept C739882 @default.
- W3205111034 hasConcept C8642999 @default.
- W3205111034 hasConceptScore W3205111034C101468663 @default.
- W3205111034 hasConceptScore W3205111034C101738243 @default.
- W3205111034 hasConceptScore W3205111034C108583219 @default.
- W3205111034 hasConceptScore W3205111034C111919701 @default.
- W3205111034 hasConceptScore W3205111034C119857082 @default.
- W3205111034 hasConceptScore W3205111034C153180895 @default.
- W3205111034 hasConceptScore W3205111034C154945302 @default.
- W3205111034 hasConceptScore W3205111034C36464697 @default.
- W3205111034 hasConceptScore W3205111034C41008148 @default.
- W3205111034 hasConceptScore W3205111034C739882 @default.
- W3205111034 hasConceptScore W3205111034C8642999 @default.
- W3205111034 hasLocation W32051110341 @default.
- W3205111034 hasOpenAccess W3205111034 @default.
- W3205111034 hasPrimaryLocation W32051110341 @default.
- W3205111034 hasRelatedWork W2576264401 @default.
- W3205111034 hasRelatedWork W2587789887 @default.
- W3205111034 hasRelatedWork W3044458868 @default.
- W3205111034 hasRelatedWork W4213225422 @default.
- W3205111034 hasRelatedWork W4281616679 @default.
- W3205111034 hasRelatedWork W4283697347 @default.
- W3205111034 hasRelatedWork W4295309597 @default.
- W3205111034 hasRelatedWork W4298144215 @default.
- W3205111034 hasRelatedWork W4307195028 @default.
- W3205111034 hasRelatedWork W4309113015 @default.
- W3205111034 isParatext "false" @default.
- W3205111034 isRetracted "false" @default.
- W3205111034 magId "3205111034" @default.
- W3205111034 workType "article" @default.