Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963662610> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2963662610 abstract "Understanding the spatial arrangement and nature of real-world objects is of paramount importance to many complex engineering tasks, including autonomous navigation. Deep learning has revolutionized state-of-the-art performance for tasks in 3D environments; however, relatively little is known about the robustness of these approaches in an adversarial setting. The lack of comprehensive analysis makes it difficult to justify deployment of 3D deep learning models in real-world, safety-critical applications. In this work, we develop an algorithm for analysis of pointwise robustness of neural networks that operate on 3D data. We show that current approaches presented for understanding the resilience of state-of-the-art models vastly overestimate their robustness. We then use our algorithm to evaluate an array of state-of-the-art models in order to demonstrate their vulnerability to occlusion attacks. We show that, in the worst case, these networks can be reduced to 0% classification accuracy after the occlusion of at most 6.5% of the occupied input space." @default.
- W2963662610 created "2019-07-30" @default.
- W2963662610 creator A5006299169 @default.
- W2963662610 creator A5081710233 @default.
- W2963662610 date "2019-06-01" @default.
- W2963662610 modified "2023-09-24" @default.
- W2963662610 title "Robustness of 3D Deep Learning in an Adversarial Setting" @default.
- W2963662610 cites W1493004075 @default.
- W2963662610 cites W1644641054 @default.
- W2963662610 cites W2140090057 @default.
- W2963662610 cites W2150066425 @default.
- W2963662610 cites W2180612164 @default.
- W2963662610 cites W2211722331 @default.
- W2963662610 cites W2293349265 @default.
- W2963662610 cites W2555618208 @default.
- W2963662610 cites W2603766943 @default.
- W2963662610 cites W2799199435 @default.
- W2963662610 cites W2800473699 @default.
- W2963662610 cites W2963208512 @default.
- W2963662610 cites W2963662610 @default.
- W2963662610 cites W2963727135 @default.
- W2963662610 cites W2963857521 @default.
- W2963662610 cites W2964062501 @default.
- W2963662610 cites W2965020757 @default.
- W2963662610 doi "https://doi.org/10.1109/cvpr.2019.01204" @default.
- W2963662610 hasPublicationYear "2019" @default.
- W2963662610 type Work @default.
- W2963662610 sameAs 2963662610 @default.
- W2963662610 citedByCount "63" @default.
- W2963662610 countsByYear W29636626102019 @default.
- W2963662610 countsByYear W29636626102020 @default.
- W2963662610 countsByYear W29636626102021 @default.
- W2963662610 countsByYear W29636626102022 @default.
- W2963662610 countsByYear W29636626102023 @default.
- W2963662610 crossrefType "proceedings-article" @default.
- W2963662610 hasAuthorship W2963662610A5006299169 @default.
- W2963662610 hasAuthorship W2963662610A5081710233 @default.
- W2963662610 hasBestOaLocation W29636626102 @default.
- W2963662610 hasConcept C104317684 @default.
- W2963662610 hasConcept C108583219 @default.
- W2963662610 hasConcept C119857082 @default.
- W2963662610 hasConcept C154945302 @default.
- W2963662610 hasConcept C185592680 @default.
- W2963662610 hasConcept C37736160 @default.
- W2963662610 hasConcept C41008148 @default.
- W2963662610 hasConcept C55493867 @default.
- W2963662610 hasConcept C63479239 @default.
- W2963662610 hasConceptScore W2963662610C104317684 @default.
- W2963662610 hasConceptScore W2963662610C108583219 @default.
- W2963662610 hasConceptScore W2963662610C119857082 @default.
- W2963662610 hasConceptScore W2963662610C154945302 @default.
- W2963662610 hasConceptScore W2963662610C185592680 @default.
- W2963662610 hasConceptScore W2963662610C37736160 @default.
- W2963662610 hasConceptScore W2963662610C41008148 @default.
- W2963662610 hasConceptScore W2963662610C55493867 @default.
- W2963662610 hasConceptScore W2963662610C63479239 @default.
- W2963662610 hasLocation W29636626101 @default.
- W2963662610 hasLocation W29636626102 @default.
- W2963662610 hasLocation W29636626103 @default.
- W2963662610 hasOpenAccess W2963662610 @default.
- W2963662610 hasPrimaryLocation W29636626101 @default.
- W2963662610 hasRelatedWork W2610321374 @default.
- W2963662610 hasRelatedWork W2952919291 @default.
- W2963662610 hasRelatedWork W3193857078 @default.
- W2963662610 hasRelatedWork W4221150850 @default.
- W2963662610 hasRelatedWork W4223943233 @default.
- W2963662610 hasRelatedWork W4224952001 @default.
- W2963662610 hasRelatedWork W4225161397 @default.
- W2963662610 hasRelatedWork W4303857474 @default.
- W2963662610 hasRelatedWork W4309045103 @default.
- W2963662610 hasRelatedWork W4312200629 @default.
- W2963662610 isParatext "false" @default.
- W2963662610 isRetracted "false" @default.
- W2963662610 magId "2963662610" @default.
- W2963662610 workType "article" @default.