FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386075951> ?p ?o ?g. }

• W4386075951 abstract "Semantic perception is a core building block in autonomous driving, since it provides information about the drivable space and location of other traffic participants. For learning-based perception, often a large amount of diverse training data is necessary to achieve high performance. Data labeling is usually a bottleneck for developing such methods, especially for dense prediction tasks, e.g., semantic segmentation or panoptic segmentation. For 3D Li-DAR data, the annotation process demands even more effort than for images. Especially in autonomous driving, point clouds are sparse, and objects appearance depends on its distance from the sensor, making it harder to acquire large amounts of labeled training data. This paper aims at taking an alternative path proposing a self-supervised representation learning method for 3D LiDAR data. Our approach exploits the vehicle motion to match objects across time viewed in different scans. We then train a model to maximize the point-wise feature similarities from points of the associated object in different scans, which enables to learn a consistent representation across time. The experimental results show that our approach performs better than previous state-of-the-art self-supervised representation learning methods when fine-tuning to different downstream tasks. We furthermore show that with only 10% of labeled data, a network pre-trained with our approach can achieve better performance than the same network trained from scratch with all labels for semantic segmentation on SemanticKITTI. <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> Code: https://github.com/PRBonn/TARL" @default.
• W4386075951 created "2023-08-23" @default.
• W4386075951 creator A5010951584 @default.
• W4386075951 creator A5011166267 @default.
• W4386075951 creator A5012654952 @default.
• W4386075951 creator A5032262344 @default.
• W4386075951 creator A5040103218 @default.
• W4386075951 creator A5068364473 @default.
• W4386075951 date "2023-06-01" @default.
• W4386075951 modified "2023-09-27" @default.
• W4386075951 title "Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving" @default.
• W4386075951 cites W2009049007 @default.
• W4386075951 cites W2150066425 @default.
• W4386075951 cites W2805521962 @default.
• W4386075951 cites W2949708697 @default.
• W4386075951 cites W2963125977 @default.
• W4386075951 cites W2963182550 @default.
• W4386075951 cites W2966975099 @default.
• W4386075951 cites W2967009971 @default.
• W4386075951 cites W2968296999 @default.
• W4386075951 cites W2981199548 @default.
• W4386075951 cites W2982683655 @default.
• W4386075951 cites W2990613095 @default.
• W4386075951 cites W2991216808 @default.
• W4386075951 cites W3034681945 @default.
• W4386075951 cites W3034781633 @default.
• W4386075951 cites W3035524453 @default.
• W4386075951 cites W3097823560 @default.
• W4386075951 cites W3109154950 @default.
• W4386075951 cites W3113328489 @default.
• W4386075951 cites W3119708198 @default.
• W4386075951 cites W3122412340 @default.
• W4386075951 cites W3129377622 @default.
• W4386075951 cites W3129559111 @default.
• W4386075951 cites W3130044230 @default.
• W4386075951 cites W3138516171 @default.
• W4386075951 cites W3145450063 @default.
• W4386075951 cites W3159481202 @default.
• W4386075951 cites W3161855852 @default.
• W4386075951 cites W3164083741 @default.
• W4386075951 cites W3165938948 @default.
• W4386075951 cites W3166573884 @default.
• W4386075951 cites W3166975282 @default.
• W4386075951 cites W3168181468 @default.
• W4386075951 cites W3168659596 @default.
• W4386075951 cites W3168822201 @default.
• W4386075951 cites W3171007011 @default.
• W4386075951 cites W3172316935 @default.
• W4386075951 cites W3172942063 @default.
• W4386075951 cites W3174527233 @default.
• W4386075951 cites W3175269419 @default.
• W4386075951 cites W3177015573 @default.
• W4386075951 cites W3177330511 @default.
• W4386075951 cites W3198790326 @default.
• W4386075951 cites W3202611145 @default.
• W4386075951 cites W3203066970 @default.
• W4386075951 cites W4205588343 @default.
• W4386075951 cites W4206778101 @default.
• W4386075951 cites W4214624153 @default.
• W4386075951 cites W4285110186 @default.
• W4386075951 cites W4287073192 @default.
• W4386075951 cites W4312270234 @default.
• W4386075951 cites W4312312750 @default.
• W4386075951 cites W4312317653 @default.
• W4386075951 cites W4312442876 @default.
• W4386075951 cites W4312536164 @default.
• W4386075951 cites W4312828305 @default.
• W4386075951 cites W4312849330 @default.
• W4386075951 cites W4312950653 @default.
• W4386075951 cites W4312977443 @default.
• W4386075951 doi "https://doi.org/10.1109/cvpr52729.2023.00505" @default.
• W4386075951 hasPublicationYear "2023" @default.
• W4386075951 type Work @default.
• W4386075951 citedByCount "0" @default.
• W4386075951 crossrefType "proceedings-article" @default.
• W4386075951 hasAuthorship W4386075951A5010951584 @default.
• W4386075951 hasAuthorship W4386075951A5011166267 @default.
• W4386075951 hasAuthorship W4386075951A5012654952 @default.
• W4386075951 hasAuthorship W4386075951A5032262344 @default.
• W4386075951 hasAuthorship W4386075951A5040103218 @default.
• W4386075951 hasAuthorship W4386075951A5068364473 @default.
• W4386075951 hasConcept C119857082 @default.
• W4386075951 hasConcept C131979681 @default.
• W4386075951 hasConcept C138885662 @default.
• W4386075951 hasConcept C149635348 @default.
• W4386075951 hasConcept C153180895 @default.
• W4386075951 hasConcept C154945302 @default.
• W4386075951 hasConcept C17744445 @default.
• W4386075951 hasConcept C199360897 @default.
• W4386075951 hasConcept C199539241 @default.
• W4386075951 hasConcept C2776359362 @default.
• W4386075951 hasConcept C2776401178 @default.
• W4386075951 hasConcept C2780513914 @default.
• W4386075951 hasConcept C31972630 @default.
• W4386075951 hasConcept C41008148 @default.
• W4386075951 hasConcept C41895202 @default.
• W4386075951 hasConcept C43521106 @default.
• W4386075951 hasConcept C59404180 @default.
• W4386075951 hasConcept C89600930 @default.
• W4386075951 hasConcept C94625758 @default.

• next