FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4363673306> ?p ?o ?g. }

• W4363673306 endingPage "23" @default.
• W4363673306 startingPage "14" @default.
• W4363673306 abstract "Adversarial robustness has attracted extensive studies in various fields by increasing the interpretability of deep learning and enhancing the understanding of neural network models. In realistic scenarios such as UAV control system, imbalanced datasets are a consensus. Therefore, how to solve the adversarial robustness on imbalanced datasets is a more and more inescapable problem in UAV control system. There have been some works on adversarial robustness on imbalanced datasets, which bring us a deeper understanding of vulnerability of deep neural networks and the generation of adversarial examples. To adjust the classification plane after training, the long-tailed robustness framework is usually designed to be multi-stage, and different classifiers are used in different stages, which can improve the robustness through multi learning. The existing methods are hardly considered to effectively handle the long-tailed robustness problem in UAV control system. To explore the intrinsic features of long-tailed robustness, we propose a one-stage robustness framework. First, we study different classifiers and propose a general cosine classifier. By changing the general cosine classifier adaptively, the model obtains a more robust classification. Then, we analyze the scalability of the focal loss and design a focal-margin loss. Finally, we design a category focus mobile learning strategy, obtained more robust features by changing the learning emphasis with this strategy. From this, we design a simple and efficient one-stage dynamic adversarial robustness method DRL under long-tailed distribution, which consists of an adaptive cosine classifier and a focal-margin loss under long-tailed mobile learning. The extended experiments demonstrate the superiority of our approach over other state-of-the-art methods, and the effectiveness of the designed module. This method can effectively solve the long-tailed robustness problem on UAV control system and other terminals." @default.
• W4363673306 created "2023-04-11" @default.
• W4363673306 creator A5011904390 @default.
• W4363673306 creator A5020805030 @default.
• W4363673306 creator A5041572932 @default.
• W4363673306 creator A5047979284 @default.
• W4363673306 creator A5060426175 @default.
• W4363673306 date "2023-05-01" @default.
• W4363673306 modified "2023-10-01" @default.
• W4363673306 title "DRL: Dynamic rebalance learning for adversarial robustness of UAV with long-tailed distribution" @default.
• W4363673306 cites W1608733719 @default.
• W4363673306 cites W2194775991 @default.
• W4363673306 cites W2440599146 @default.
• W4363673306 cites W2607219512 @default.
• W4363673306 cites W2767106145 @default.
• W4363673306 cites W2774644650 @default.
• W4363673306 cites W2809379039 @default.
• W4363673306 cites W2884561390 @default.
• W4363673306 cites W2897712612 @default.
• W4363673306 cites W2954996726 @default.
• W4363673306 cites W2962700793 @default.
• W4363673306 cites W2963184668 @default.
• W4363673306 cites W2963691377 @default.
• W4363673306 cites W2963857521 @default.
• W4363673306 cites W2968625502 @default.
• W4363673306 cites W2970084480 @default.
• W4363673306 cites W2991288769 @default.
• W4363673306 cites W3000094279 @default.
• W4363673306 cites W3006558576 @default.
• W4363673306 cites W3034369739 @default.
• W4363673306 cites W3034537217 @default.
• W4363673306 cites W3036999909 @default.
• W4363673306 cites W3040248848 @default.
• W4363673306 cites W3096688134 @default.
• W4363673306 cites W3103152812 @default.
• W4363673306 cites W3159935161 @default.
• W4363673306 cites W3166596953 @default.
• W4363673306 cites W3171998492 @default.
• W4363673306 cites W3176346992 @default.
• W4363673306 cites W3209306061 @default.
• W4363673306 cites W3211999566 @default.
• W4363673306 cites W4214576162 @default.
• W4363673306 cites W4224144197 @default.
• W4363673306 cites W4285502143 @default.
• W4363673306 cites W4311049322 @default.
• W4363673306 doi "https://doi.org/10.1016/j.comcom.2023.04.002" @default.
• W4363673306 hasPublicationYear "2023" @default.
• W4363673306 type Work @default.
• W4363673306 citedByCount "2" @default.
• W4363673306 countsByYear W43636733062023 @default.
• W4363673306 crossrefType "journal-article" @default.
• W4363673306 hasAuthorship W4363673306A5011904390 @default.
• W4363673306 hasAuthorship W4363673306A5020805030 @default.
• W4363673306 hasAuthorship W4363673306A5041572932 @default.
• W4363673306 hasAuthorship W4363673306A5047979284 @default.
• W4363673306 hasAuthorship W4363673306A5060426175 @default.
• W4363673306 hasConcept C104317684 @default.
• W4363673306 hasConcept C108583219 @default.
• W4363673306 hasConcept C119857082 @default.
• W4363673306 hasConcept C154945302 @default.
• W4363673306 hasConcept C185592680 @default.
• W4363673306 hasConcept C2781067378 @default.
• W4363673306 hasConcept C37736160 @default.
• W4363673306 hasConcept C41008148 @default.
• W4363673306 hasConcept C50644808 @default.
• W4363673306 hasConcept C55493867 @default.
• W4363673306 hasConcept C63479239 @default.
• W4363673306 hasConcept C95623464 @default.
• W4363673306 hasConceptScore W4363673306C104317684 @default.
• W4363673306 hasConceptScore W4363673306C108583219 @default.
• W4363673306 hasConceptScore W4363673306C119857082 @default.
• W4363673306 hasConceptScore W4363673306C154945302 @default.
• W4363673306 hasConceptScore W4363673306C185592680 @default.
• W4363673306 hasConceptScore W4363673306C2781067378 @default.
• W4363673306 hasConceptScore W4363673306C37736160 @default.
• W4363673306 hasConceptScore W4363673306C41008148 @default.
• W4363673306 hasConceptScore W4363673306C50644808 @default.
• W4363673306 hasConceptScore W4363673306C55493867 @default.
• W4363673306 hasConceptScore W4363673306C63479239 @default.
• W4363673306 hasConceptScore W4363673306C95623464 @default.
• W4363673306 hasLocation W43636733061 @default.
• W4363673306 hasOpenAccess W4363673306 @default.
• W4363673306 hasPrimaryLocation W43636733061 @default.
• W4363673306 hasRelatedWork W2605281151 @default.
• W4363673306 hasRelatedWork W2952919291 @default.
• W4363673306 hasRelatedWork W3006943036 @default.
• W4363673306 hasRelatedWork W3191046242 @default.
• W4363673306 hasRelatedWork W3193857078 @default.
• W4363673306 hasRelatedWork W3208304128 @default.
• W4363673306 hasRelatedWork W4213225422 @default.
• W4363673306 hasRelatedWork W4294031299 @default.
• W4363673306 hasRelatedWork W4299487748 @default.
• W4363673306 hasRelatedWork W4310989423 @default.
• W4363673306 hasVolume "205" @default.
• W4363673306 isParatext "false" @default.
• W4363673306 isRetracted "false" @default.
• W4363673306 workType "article" @default.