Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208668203> ?p ?o ?g. }
- W3208668203 abstract "Deep Generative Models (DGMs) are known for their superior capability in generating realistic data. Extending purely data-driven approaches, recent specialized DGMs may satisfy additional controllable requirements such as embedding a traffic sign in a driving scene, by manipulating patterns textit{implicitly} in the neuron or feature level. In this paper, we introduce a novel method to incorporate domain knowledge textit{explicitly} in the generation process to achieve semantically controllable scene generation. We categorize our knowledge into two types to be consistent with the composition of natural scenes, where the first type represents the property of objects and the second type represents the relationship among objects. We then propose a tree-structured generative model to learn complex scene representation, whose nodes and edges are naturally corresponding to the two types of knowledge respectively. Knowledge can be explicitly integrated to enable semantically controllable scene generation by imposing semantic rules on properties of nodes and edges in the tree structure. We construct a synthetic example to illustrate the controllability and explainability of our method in a clean setting. We further extend the synthetic example to realistic autonomous vehicle driving environments and conduct extensive experiments to show that our method efficiently identifies adversarial traffic scenes against different state-of-the-art 3D point cloud segmentation models satisfying the traffic rules specified as the explicit knowledge." @default.
- W3208668203 created "2021-11-08" @default.
- W3208668203 creator A5034995105 @default.
- W3208668203 creator A5037644321 @default.
- W3208668203 creator A5047535950 @default.
- W3208668203 creator A5058280572 @default.
- W3208668203 date "2021-10-28" @default.
- W3208668203 modified "2023-09-27" @default.
- W3208668203 title "Semantically Controllable Generation of Physical Scenes with Explicit Knowledge." @default.
- W3208668203 cites W1423339008 @default.
- W3208668203 cites W1777239053 @default.
- W3208668203 cites W1959608418 @default.
- W3208668203 cites W2001098248 @default.
- W3208668203 cites W2002827932 @default.
- W3208668203 cites W2016589492 @default.
- W3208668203 cites W2154368244 @default.
- W3208668203 cites W2175031088 @default.
- W3208668203 cites W2311110368 @default.
- W3208668203 cites W2327562811 @default.
- W3208668203 cites W2409550820 @default.
- W3208668203 cites W2468462628 @default.
- W3208668203 cites W2572147858 @default.
- W3208668203 cites W2739010165 @default.
- W3208668203 cites W2786565076 @default.
- W3208668203 cites W2799123546 @default.
- W3208668203 cites W2807242871 @default.
- W3208668203 cites W2888429796 @default.
- W3208668203 cites W2893749619 @default.
- W3208668203 cites W2903538854 @default.
- W3208668203 cites W2903926864 @default.
- W3208668203 cites W2915002466 @default.
- W3208668203 cites W2950096400 @default.
- W3208668203 cites W2952911150 @default.
- W3208668203 cites W2955189650 @default.
- W3208668203 cites W2958109694 @default.
- W3208668203 cites W2962770929 @default.
- W3208668203 cites W2962818872 @default.
- W3208668203 cites W2963068442 @default.
- W3208668203 cites W2963121255 @default.
- W3208668203 cites W2963527086 @default.
- W3208668203 cites W2963601843 @default.
- W3208668203 cites W2963676163 @default.
- W3208668203 cites W2963801305 @default.
- W3208668203 cites W2963819570 @default.
- W3208668203 cites W2964108670 @default.
- W3208668203 cites W2968638474 @default.
- W3208668203 cites W2968993450 @default.
- W3208668203 cites W2970971581 @default.
- W3208668203 cites W2985068832 @default.
- W3208668203 cites W2985936292 @default.
- W3208668203 cites W2991216808 @default.
- W3208668203 cites W2996582215 @default.
- W3208668203 cites W3034455297 @default.
- W3208668203 cites W3034716600 @default.
- W3208668203 cites W3035275207 @default.
- W3208668203 cites W3035314354 @default.
- W3208668203 cites W3035355202 @default.
- W3208668203 cites W3042890712 @default.
- W3208668203 cites W3043461357 @default.
- W3208668203 cites W3048723201 @default.
- W3208668203 cites W3082665562 @default.
- W3208668203 cites W3099760900 @default.
- W3208668203 cites W3109385784 @default.
- W3208668203 cites W3109621557 @default.
- W3208668203 cites W3109944402 @default.
- W3208668203 cites W3110015970 @default.
- W3208668203 cites W3113144764 @default.
- W3208668203 cites W3123505479 @default.
- W3208668203 cites W3123911832 @default.
- W3208668203 cites W3125423558 @default.
- W3208668203 cites W3126940265 @default.
- W3208668203 cites W3133465684 @default.
- W3208668203 cites W3148140980 @default.
- W3208668203 cites W3145738572 @default.
- W3208668203 hasPublicationYear "2021" @default.
- W3208668203 type Work @default.
- W3208668203 sameAs 3208668203 @default.
- W3208668203 citedByCount "0" @default.
- W3208668203 crossrefType "posted-content" @default.
- W3208668203 hasAuthorship W3208668203A5034995105 @default.
- W3208668203 hasAuthorship W3208668203A5037644321 @default.
- W3208668203 hasAuthorship W3208668203A5047535950 @default.
- W3208668203 hasAuthorship W3208668203A5058280572 @default.
- W3208668203 hasConcept C111472728 @default.
- W3208668203 hasConcept C111919701 @default.
- W3208668203 hasConcept C113174947 @default.
- W3208668203 hasConcept C131979681 @default.
- W3208668203 hasConcept C134306372 @default.
- W3208668203 hasConcept C138885662 @default.
- W3208668203 hasConcept C154945302 @default.
- W3208668203 hasConcept C167966045 @default.
- W3208668203 hasConcept C17744445 @default.
- W3208668203 hasConcept C189950617 @default.
- W3208668203 hasConcept C199360897 @default.
- W3208668203 hasConcept C199539241 @default.
- W3208668203 hasConcept C207685749 @default.
- W3208668203 hasConcept C2776359362 @default.
- W3208668203 hasConcept C2776401178 @default.
- W3208668203 hasConcept C2780801425 @default.
- W3208668203 hasConcept C28826006 @default.