Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201877816> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3201877816 abstract "Modern object detectors are vulnerable to adversarial examples, which brings potential risks to numerous applications, e.g., self-driving car. Among attacks regularized by $ell_p$ norm, $ell_0$-attack aims to modify as few pixels as possible. Nevertheless, the problem is nontrivial since it generally requires to optimize the shape along with the texture simultaneously, which is an NP-hard problem. To address this issue, we propose a novel method of Adversarial Semantic Contour (ASC) guided by object contour as prior. With this prior, we reduce the searching space to accelerate the $ell_0$ optimization, and also introduce more semantic information which should affect the detectors more. Based on the contour, we optimize the selection of modified pixels via sampling and their colors with gradient descent alternately. Extensive experiments demonstrate that our proposed ASC outperforms the most commonly manually designed patterns (e.g., square patches and grids) on task of disappearing. By modifying no more than 5% and 3.5% of the object area respectively, our proposed ASC can successfully mislead the mainstream object detectors including the SSD512, Yolov4, Mask RCNN, Faster RCNN, etc." @default.
- W3201877816 created "2021-10-11" @default.
- W3201877816 creator A5003713785 @default.
- W3201877816 creator A5025588570 @default.
- W3201877816 creator A5033410733 @default.
- W3201877816 creator A5078699661 @default.
- W3201877816 date "2021-09-30" @default.
- W3201877816 modified "2023-09-27" @default.
- W3201877816 title "Adversarial Semantic Contour for Object Detection" @default.
- W3201877816 cites W2128715914 @default.
- W3201877816 cites W2613718673 @default.
- W3201877816 cites W2796347433 @default.
- W3201877816 cites W2950141105 @default.
- W3201877816 cites W2951433694 @default.
- W3201877816 cites W2952122856 @default.
- W3201877816 cites W2963037989 @default.
- W3201877816 cites W2963726920 @default.
- W3201877816 cites W2964253222 @default.
- W3201877816 cites W3017485054 @default.
- W3201877816 cites W3018757597 @default.
- W3201877816 cites W3024232493 @default.
- W3201877816 cites W3093958125 @default.
- W3201877816 cites W3106250896 @default.
- W3201877816 hasPublicationYear "2021" @default.
- W3201877816 type Work @default.
- W3201877816 sameAs 3201877816 @default.
- W3201877816 citedByCount "0" @default.
- W3201877816 crossrefType "posted-content" @default.
- W3201877816 hasAuthorship W3201877816A5003713785 @default.
- W3201877816 hasAuthorship W3201877816A5025588570 @default.
- W3201877816 hasAuthorship W3201877816A5033410733 @default.
- W3201877816 hasAuthorship W3201877816A5078699661 @default.
- W3201877816 hasConcept C153180895 @default.
- W3201877816 hasConcept C153258448 @default.
- W3201877816 hasConcept C154945302 @default.
- W3201877816 hasConcept C160633673 @default.
- W3201877816 hasConcept C17744445 @default.
- W3201877816 hasConcept C191795146 @default.
- W3201877816 hasConcept C199539241 @default.
- W3201877816 hasConcept C2776151529 @default.
- W3201877816 hasConcept C2781238097 @default.
- W3201877816 hasConcept C31972630 @default.
- W3201877816 hasConcept C37736160 @default.
- W3201877816 hasConcept C41008148 @default.
- W3201877816 hasConcept C50644808 @default.
- W3201877816 hasConcept C76155785 @default.
- W3201877816 hasConcept C81917197 @default.
- W3201877816 hasConcept C94915269 @default.
- W3201877816 hasConceptScore W3201877816C153180895 @default.
- W3201877816 hasConceptScore W3201877816C153258448 @default.
- W3201877816 hasConceptScore W3201877816C154945302 @default.
- W3201877816 hasConceptScore W3201877816C160633673 @default.
- W3201877816 hasConceptScore W3201877816C17744445 @default.
- W3201877816 hasConceptScore W3201877816C191795146 @default.
- W3201877816 hasConceptScore W3201877816C199539241 @default.
- W3201877816 hasConceptScore W3201877816C2776151529 @default.
- W3201877816 hasConceptScore W3201877816C2781238097 @default.
- W3201877816 hasConceptScore W3201877816C31972630 @default.
- W3201877816 hasConceptScore W3201877816C37736160 @default.
- W3201877816 hasConceptScore W3201877816C41008148 @default.
- W3201877816 hasConceptScore W3201877816C50644808 @default.
- W3201877816 hasConceptScore W3201877816C76155785 @default.
- W3201877816 hasConceptScore W3201877816C81917197 @default.
- W3201877816 hasConceptScore W3201877816C94915269 @default.
- W3201877816 hasLocation W32018778161 @default.
- W3201877816 hasOpenAccess W3201877816 @default.
- W3201877816 hasPrimaryLocation W32018778161 @default.
- W3201877816 hasRelatedWork W1610263463 @default.
- W3201877816 hasRelatedWork W1969653662 @default.
- W3201877816 hasRelatedWork W2126096326 @default.
- W3201877816 hasRelatedWork W2132156145 @default.
- W3201877816 hasRelatedWork W2562152415 @default.
- W3201877816 hasRelatedWork W2605205826 @default.
- W3201877816 hasRelatedWork W2751330204 @default.
- W3201877816 hasRelatedWork W2914474519 @default.
- W3201877816 hasRelatedWork W2935594133 @default.
- W3201877816 hasRelatedWork W2951624519 @default.
- W3201877816 hasRelatedWork W2952229497 @default.
- W3201877816 hasRelatedWork W2963679518 @default.
- W3201877816 hasRelatedWork W3019200386 @default.
- W3201877816 hasRelatedWork W3110554406 @default.
- W3201877816 hasRelatedWork W3134387240 @default.
- W3201877816 hasRelatedWork W3137765971 @default.
- W3201877816 hasRelatedWork W3138552274 @default.
- W3201877816 hasRelatedWork W3174463325 @default.
- W3201877816 hasRelatedWork W3195555194 @default.
- W3201877816 hasRelatedWork W3213959871 @default.
- W3201877816 isParatext "false" @default.
- W3201877816 isRetracted "false" @default.
- W3201877816 magId "3201877816" @default.
- W3201877816 workType "article" @default.