FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313128851> ?p ?o ?g. }

• W4313128851 abstract "Segmenting or detecting objects in sparse Lidar point clouds are two important tasks in autonomous driving to allow a vehicle to act safely in its 3D environment. The best performing methods in 3D semantic segmentation or object detection rely on a large amount of annotated data. Yet annotating 3D Lidar data for these tasks is tedious and costly. In this context, we propose a self-supervised pretraining method for 3D perception models that is tailored to autonomous driving data. Specifically, we leverage the availability of synchronized and calibrated image and Lidar sensors in autonomous driving setups for distilling self-supervised pre-trained image representations into 3D models. Hence, our method does not require any point cloud nor image annotations. The keyingredient of our method is the use of superpixels which are used to pool 3D point features and 2D pixel features in visually similar regions. We then train a 3D network on the self-supervised task of matching these pooled point features with the corresponding pooled image pixel features. The advantages of contrasting regions obtained by superpixels are that: (1) grouping together pixels and points of visually coherent regions leads to a more meaningful contrastive task that produces features well adapted to 3D semantic segmentation and 3D object detection; (2) all the different regions have the same weight in the contrastive loss regardless of the number of 3D points sampled in these regions; (3) it mitigates the noise produced by incorrect matching of points and pixels due to occlusions between the different sensors. Extensive experiments on autonomous driving datasets demonstrate the ability of our image-to-Lidar distillation strategy to produce 3D representations that transfer well on semantic segmentation and object detection tasks." @default.
• W4313128851 created "2023-01-06" @default.
• W4313128851 creator A5003783466 @default.
• W4313128851 creator A5032376404 @default.
• W4313128851 creator A5041253713 @default.
• W4313128851 creator A5047737542 @default.
• W4313128851 creator A5065544923 @default.
• W4313128851 creator A5070809773 @default.
• W4313128851 date "2022-06-01" @default.
• W4313128851 modified "2023-10-06" @default.
• W4313128851 title "Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data" @default.
• W4313128851 cites W1999478155 @default.
• W4313128851 cites W2117539524 @default.
• W4313128851 cites W2118246710 @default.
• W4313128851 cites W2138621090 @default.
• W4313128851 cites W2150066425 @default.
• W4313128851 cites W2194775991 @default.
• W4313128851 cites W2294370754 @default.
• W4313128851 cites W2795587607 @default.
• W4313128851 cites W2963125977 @default.
• W4313128851 cites W2963420272 @default.
• W4313128851 cites W2963727135 @default.
• W4313128851 cites W2982683655 @default.
• W4313128851 cites W2991216808 @default.
• W4313128851 cites W2991485494 @default.
• W4313128851 cites W2998388430 @default.
• W4313128851 cites W3018265077 @default.
• W4313128851 cites W3034781633 @default.
• W4313128851 cites W3035524453 @default.
• W4313128851 cites W3035750252 @default.
• W4313128851 cites W3097823560 @default.
• W4313128851 cites W3119708198 @default.
• W4313128851 cites W3122240496 @default.
• W4313128851 cites W3128716822 @default.
• W4313128851 cites W3129110783 @default.
• W4313128851 cites W3159481202 @default.
• W4313128851 cites W3166573884 @default.
• W4313128851 cites W3168822201 @default.
• W4313128851 cites W3171007011 @default.
• W4313128851 cites W3172456032 @default.
• W4313128851 cites W3172615411 @default.
• W4313128851 cites W3173636389 @default.
• W4313128851 cites W3177330511 @default.
• W4313128851 cites W3178738710 @default.
• W4313128851 cites W3184000328 @default.
• W4313128851 cites W3202611145 @default.
• W4313128851 cites W3203089644 @default.
• W4313128851 cites W3203240897 @default.
• W4313128851 cites W3210964660 @default.
• W4313128851 cites W343636949 @default.
• W4313128851 cites W4214504406 @default.
• W4313128851 cites W4214638047 @default.
• W4313128851 cites W4226389400 @default.
• W4313128851 cites W753847829 @default.
• W4313128851 doi "https://doi.org/10.1109/cvpr52688.2022.00966" @default.
• W4313128851 hasPublicationYear "2022" @default.
• W4313128851 type Work @default.
• W4313128851 citedByCount "15" @default.
• W4313128851 countsByYear W43131288512023 @default.
• W4313128851 crossrefType "proceedings-article" @default.
• W4313128851 hasAuthorship W4313128851A5003783466 @default.
• W4313128851 hasAuthorship W4313128851A5032376404 @default.
• W4313128851 hasAuthorship W4313128851A5041253713 @default.
• W4313128851 hasAuthorship W4313128851A5047737542 @default.
• W4313128851 hasAuthorship W4313128851A5065544923 @default.
• W4313128851 hasAuthorship W4313128851A5070809773 @default.
• W4313128851 hasBestOaLocation W43131288512 @default.
• W4313128851 hasConcept C105795698 @default.
• W4313128851 hasConcept C115961682 @default.
• W4313128851 hasConcept C124504099 @default.
• W4313128851 hasConcept C127313418 @default.
• W4313128851 hasConcept C131979681 @default.
• W4313128851 hasConcept C151730666 @default.
• W4313128851 hasConcept C153083717 @default.
• W4313128851 hasConcept C153180895 @default.
• W4313128851 hasConcept C154945302 @default.
• W4313128851 hasConcept C160633673 @default.
• W4313128851 hasConcept C165064840 @default.
• W4313128851 hasConcept C2776151529 @default.
• W4313128851 hasConcept C2779343474 @default.
• W4313128851 hasConcept C2779662243 @default.
• W4313128851 hasConcept C31972630 @default.
• W4313128851 hasConcept C33923547 @default.
• W4313128851 hasConcept C41008148 @default.
• W4313128851 hasConcept C51399673 @default.
• W4313128851 hasConcept C62649853 @default.
• W4313128851 hasConcept C86803240 @default.
• W4313128851 hasConcept C89600930 @default.
• W4313128851 hasConceptScore W4313128851C105795698 @default.
• W4313128851 hasConceptScore W4313128851C115961682 @default.
• W4313128851 hasConceptScore W4313128851C124504099 @default.
• W4313128851 hasConceptScore W4313128851C127313418 @default.
• W4313128851 hasConceptScore W4313128851C131979681 @default.
• W4313128851 hasConceptScore W4313128851C151730666 @default.
• W4313128851 hasConceptScore W4313128851C153083717 @default.
• W4313128851 hasConceptScore W4313128851C153180895 @default.
• W4313128851 hasConceptScore W4313128851C154945302 @default.
• W4313128851 hasConceptScore W4313128851C160633673 @default.
• W4313128851 hasConceptScore W4313128851C165064840 @default.
• W4313128851 hasConceptScore W4313128851C2776151529 @default.

• next