Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312924930> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4312924930 abstract "Advances in deep learning have resulted in steady progress in computer vision with improved accuracy on tasks such as object detection and semantic segmentation. Nevertheless, deep neural networks are vulnerable to adversarial attacks, thus presenting a challenge in reliable deployment. Two of the prominent tasks in 3D scene-understanding for robotics and advanced drive assistance systems are monocular depth and pose estimation, often learned together in an unsupervised manner. While studies evaluating the impact of adversarial attacks on monocular depth estimation exist, a systematic demonstration and analysis of adversarial perturbations against pose estimation are lacking. We show how additive imperceptible perturbations can not only change predictions to increase the trajectory drift but also catastrophically alter its geometry. We also study the relation between adversarial perturbations targeting monocular depth and pose estimation networks, as well as the transferability of perturbations to other networks with different architectures and losses. Our experiments show how the generated perturbations lead to notable errors in relative rotation and translation predictions and elucidate vulnerabilities of the networks." @default.
- W4312924930 created "2023-01-05" @default.
- W4312924930 creator A5028650455 @default.
- W4312924930 creator A5043042113 @default.
- W4312924930 creator A5047435371 @default.
- W4312924930 creator A5082972838 @default.
- W4312924930 date "2022-10-23" @default.
- W4312924930 modified "2023-10-16" @default.
- W4312924930 title "Adversarial Attacks on Monocular Pose Estimation" @default.
- W4312924930 cites W2150066425 @default.
- W4312924930 cites W2194775991 @default.
- W4312924930 cites W2604505099 @default.
- W4312924930 cites W2609883120 @default.
- W4312924930 cites W2963118571 @default.
- W4312924930 cites W2963178695 @default.
- W4312924930 cites W2963461686 @default.
- W4312924930 cites W2964097310 @default.
- W4312924930 cites W2967702344 @default.
- W4312924930 cites W3034604951 @default.
- W4312924930 cites W3174211490 @default.
- W4312924930 cites W3203097397 @default.
- W4312924930 cites W3207149368 @default.
- W4312924930 cites W4212860834 @default.
- W4312924930 doi "https://doi.org/10.1109/iros47612.2022.9982154" @default.
- W4312924930 hasPublicationYear "2022" @default.
- W4312924930 type Work @default.
- W4312924930 citedByCount "2" @default.
- W4312924930 countsByYear W43129249302023 @default.
- W4312924930 crossrefType "proceedings-article" @default.
- W4312924930 hasAuthorship W4312924930A5028650455 @default.
- W4312924930 hasAuthorship W4312924930A5043042113 @default.
- W4312924930 hasAuthorship W4312924930A5047435371 @default.
- W4312924930 hasAuthorship W4312924930A5082972838 @default.
- W4312924930 hasBestOaLocation W43129249302 @default.
- W4312924930 hasConcept C108583219 @default.
- W4312924930 hasConcept C119857082 @default.
- W4312924930 hasConcept C121332964 @default.
- W4312924930 hasConcept C1276947 @default.
- W4312924930 hasConcept C13662910 @default.
- W4312924930 hasConcept C140331021 @default.
- W4312924930 hasConcept C154945302 @default.
- W4312924930 hasConcept C2776151529 @default.
- W4312924930 hasConcept C2984842247 @default.
- W4312924930 hasConcept C31972630 @default.
- W4312924930 hasConcept C34413123 @default.
- W4312924930 hasConcept C37736160 @default.
- W4312924930 hasConcept C41008148 @default.
- W4312924930 hasConcept C50644808 @default.
- W4312924930 hasConcept C52102323 @default.
- W4312924930 hasConcept C61272859 @default.
- W4312924930 hasConcept C65909025 @default.
- W4312924930 hasConcept C89600930 @default.
- W4312924930 hasConcept C90509273 @default.
- W4312924930 hasConceptScore W4312924930C108583219 @default.
- W4312924930 hasConceptScore W4312924930C119857082 @default.
- W4312924930 hasConceptScore W4312924930C121332964 @default.
- W4312924930 hasConceptScore W4312924930C1276947 @default.
- W4312924930 hasConceptScore W4312924930C13662910 @default.
- W4312924930 hasConceptScore W4312924930C140331021 @default.
- W4312924930 hasConceptScore W4312924930C154945302 @default.
- W4312924930 hasConceptScore W4312924930C2776151529 @default.
- W4312924930 hasConceptScore W4312924930C2984842247 @default.
- W4312924930 hasConceptScore W4312924930C31972630 @default.
- W4312924930 hasConceptScore W4312924930C34413123 @default.
- W4312924930 hasConceptScore W4312924930C37736160 @default.
- W4312924930 hasConceptScore W4312924930C41008148 @default.
- W4312924930 hasConceptScore W4312924930C50644808 @default.
- W4312924930 hasConceptScore W4312924930C52102323 @default.
- W4312924930 hasConceptScore W4312924930C61272859 @default.
- W4312924930 hasConceptScore W4312924930C65909025 @default.
- W4312924930 hasConceptScore W4312924930C89600930 @default.
- W4312924930 hasConceptScore W4312924930C90509273 @default.
- W4312924930 hasLocation W43129249301 @default.
- W4312924930 hasLocation W43129249302 @default.
- W4312924930 hasLocation W43129249303 @default.
- W4312924930 hasOpenAccess W4312924930 @default.
- W4312924930 hasPrimaryLocation W43129249301 @default.
- W4312924930 hasRelatedWork W1628937209 @default.
- W4312924930 hasRelatedWork W1968716783 @default.
- W4312924930 hasRelatedWork W1988485990 @default.
- W4312924930 hasRelatedWork W2113039159 @default.
- W4312924930 hasRelatedWork W2144760288 @default.
- W4312924930 hasRelatedWork W2770260910 @default.
- W4312924930 hasRelatedWork W2891001608 @default.
- W4312924930 hasRelatedWork W3102636071 @default.
- W4312924930 hasRelatedWork W4224011692 @default.
- W4312924930 hasRelatedWork W4312637486 @default.
- W4312924930 isParatext "false" @default.
- W4312924930 isRetracted "false" @default.
- W4312924930 workType "article" @default.