FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281738863> ?p ?o ?g. }

• W4281738863 abstract "Edge-based and autonomous, deep learning computer vision applications, such as those used in surveillance or traffic management, must be assuredly correct and performant. However, realizing these applications in practice incurs a number of challenges. First, the constraints on edge resources precludes the use of large-sized, deep learning computer vision models. Second, the heterogeneity in edge resource types causes different execution speeds and energy consumption during model inference. Third, deep learning models are known to be vulnerable to adversarial perturbations, which can make them ineffective or lead to incorrect inferences. Although some research that addresses the first two challenges exists, defending against adversarial attacks at the edge remains mostly an unresolved problem. To that end, this paper presents techniques to realize robust and edge-based deep learning computer vision applications thereby providing a level of assured autonomy. We utilize state-of-the-art (SOTA) object detection attacks from the TOG (adversarial objectness gradient attacks) suite to design a generalized adversarial robustness evaluation procedure. It enables fast robustness evaluations on popular object detection architectures of YOLOv3, YOLOv3-tiny, and Faster R-CNN with different image classification backbones to test the robustness of these object detection models. We explore two variations of adversarial training. The first variant augments the training data with multiple types of attacks. The second variant exchanges a clean image in the training set for a randomly chosen adversarial image. Our solutions are then evaluated using the PASCAL VOC dataset. Using the first variant, we are able to improve the robustness of YOLOv3-tiny models by 1–2% mean average precision (mAP) and YOLOv3 realized an improvement of up to 17% mAP on attacked data. The second variant saw even better results in some cases with improvements in robustness of over 25% for YOLOv3. The Faster RCNN models also saw improvement, however, less substantially at around 10–15%. Yet, their mAP was improved on clean data as well." @default.
• W4281738863 created "2022-06-13" @default.
• W4281738863 creator A5002363659 @default.
• W4281738863 creator A5011261173 @default.
• W4281738863 creator A5017197472 @default.
• W4281738863 creator A5032058163 @default.
• W4281738863 creator A5072480199 @default.
• W4281738863 date "2022-03-01" @default.
• W4281738863 modified "2023-09-27" @default.
• W4281738863 title "Adversarially Robust Edge-Based Object Detection for Assuredly Autonomous Systems" @default.
• W4281738863 cites W2031489346 @default.
• W4281738863 cites W2603766943 @default.
• W4281738863 cites W2604505099 @default.
• W4281738863 cites W2954978443 @default.
• W4281738863 cites W2962872506 @default.
• W4281738863 cites W2962970995 @default.
• W4281738863 cites W2979515806 @default.
• W4281738863 cites W2989161706 @default.
• W4281738863 cites W3089073543 @default.
• W4281738863 cites W3110909937 @default.
• W4281738863 cites W3126650150 @default.
• W4281738863 cites W3142058427 @default.
• W4281738863 cites W3154528133 @default.
• W4281738863 cites W3175958943 @default.
• W4281738863 doi "https://doi.org/10.1109/icaa52185.2022.00021" @default.
• W4281738863 hasPublicationYear "2022" @default.
• W4281738863 type Work @default.
• W4281738863 citedByCount "1" @default.
• W4281738863 countsByYear W42817388632022 @default.
• W4281738863 crossrefType "proceedings-article" @default.
• W4281738863 hasAuthorship W4281738863A5002363659 @default.
• W4281738863 hasAuthorship W4281738863A5011261173 @default.
• W4281738863 hasAuthorship W4281738863A5017197472 @default.
• W4281738863 hasAuthorship W4281738863A5032058163 @default.
• W4281738863 hasAuthorship W4281738863A5072480199 @default.
• W4281738863 hasConcept C104317684 @default.
• W4281738863 hasConcept C108583219 @default.
• W4281738863 hasConcept C111919701 @default.
• W4281738863 hasConcept C119857082 @default.
• W4281738863 hasConcept C138236772 @default.
• W4281738863 hasConcept C153180895 @default.
• W4281738863 hasConcept C154945302 @default.
• W4281738863 hasConcept C185592680 @default.
• W4281738863 hasConcept C2776151529 @default.
• W4281738863 hasConcept C2776214188 @default.
• W4281738863 hasConcept C2984842247 @default.
• W4281738863 hasConcept C31972630 @default.
• W4281738863 hasConcept C37736160 @default.
• W4281738863 hasConcept C41008148 @default.
• W4281738863 hasConcept C55493867 @default.
• W4281738863 hasConcept C63479239 @default.
• W4281738863 hasConcept C79974875 @default.
• W4281738863 hasConceptScore W4281738863C104317684 @default.
• W4281738863 hasConceptScore W4281738863C108583219 @default.
• W4281738863 hasConceptScore W4281738863C111919701 @default.
• W4281738863 hasConceptScore W4281738863C119857082 @default.
• W4281738863 hasConceptScore W4281738863C138236772 @default.
• W4281738863 hasConceptScore W4281738863C153180895 @default.
• W4281738863 hasConceptScore W4281738863C154945302 @default.
• W4281738863 hasConceptScore W4281738863C185592680 @default.
• W4281738863 hasConceptScore W4281738863C2776151529 @default.
• W4281738863 hasConceptScore W4281738863C2776214188 @default.
• W4281738863 hasConceptScore W4281738863C2984842247 @default.
• W4281738863 hasConceptScore W4281738863C31972630 @default.
• W4281738863 hasConceptScore W4281738863C37736160 @default.
• W4281738863 hasConceptScore W4281738863C41008148 @default.
• W4281738863 hasConceptScore W4281738863C55493867 @default.
• W4281738863 hasConceptScore W4281738863C63479239 @default.
• W4281738863 hasConceptScore W4281738863C79974875 @default.
• W4281738863 hasLocation W42817388631 @default.
• W4281738863 hasOpenAccess W4281738863 @default.
• W4281738863 hasPrimaryLocation W42817388631 @default.
• W4281738863 hasRelatedWork W2146875012 @default.
• W4281738863 hasRelatedWork W2952919291 @default.
• W4281738863 hasRelatedWork W2970686063 @default.
• W4281738863 hasRelatedWork W3193857078 @default.
• W4281738863 hasRelatedWork W3208723233 @default.
• W4281738863 hasRelatedWork W4281738863 @default.
• W4281738863 hasRelatedWork W4292829955 @default.
• W4281738863 hasRelatedWork W4293054861 @default.
• W4281738863 hasRelatedWork W4307654699 @default.
• W4281738863 hasRelatedWork W4317552138 @default.
• W4281738863 isParatext "false" @default.
• W4281738863 isRetracted "false" @default.
• W4281738863 workType "article" @default.