Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119970108> ?p ?o ?g. }
- W3119970108 abstract "LiDAR sensors are crucial in automotive perception for accurate object detection. However, LiDAR data is hard to interpret for humans and consequently time-consuming to label. Whereas camera data is easy interpretable and thus, comparably simpler to label. Within this work we present a transductive transfer learning approach to transfer the knowledge for the object detection task from images to point cloud data. We propose a multi-modal adversarial Auto Encoder architecture which disentangles uni-modal features into two groups: common (transferable) features, and complementary (modality-specific) features. This disentanglement is based on the hypothesis that a set of common features exist. An important point of our framework is that the disentanglement is learned in an unsupervised manner. Furthermore, the results show that only a small amount of multi-modal data is needed to learn the disentanglement, and thus to transfer the knowledge between modalities. As a result we our experiments show that training with 75% less data of the KITTI objects, the classification accuracy achieved is of 71.75%, only 3.12% less than when using the full data set. The implications of these findings can have great impact in perception pipelines based on LIDAR data." @default.
- W3119970108 created "2021-01-18" @default.
- W3119970108 creator A5012503404 @default.
- W3119970108 creator A5059792297 @default.
- W3119970108 creator A5063529163 @default.
- W3119970108 creator A5083003222 @default.
- W3119970108 creator A5086523139 @default.
- W3119970108 date "2020-10-19" @default.
- W3119970108 modified "2023-09-27" @default.
- W3119970108 title "Learning Common and Transferable Feature Representations for Multi-Modal Data" @default.
- W3119970108 cites W1691728462 @default.
- W3119970108 cites W1861492603 @default.
- W3119970108 cites W1889038981 @default.
- W3119970108 cites W2052742500 @default.
- W3119970108 cites W2115579991 @default.
- W3119970108 cites W2190691619 @default.
- W3119970108 cites W2207044458 @default.
- W3119970108 cites W2465570449 @default.
- W3119970108 cites W2493603909 @default.
- W3119970108 cites W2504204199 @default.
- W3119970108 cites W2560609797 @default.
- W3119970108 cites W2560722161 @default.
- W3119970108 cites W2608295741 @default.
- W3119970108 cites W2758425594 @default.
- W3119970108 cites W2769571673 @default.
- W3119970108 cites W2788994472 @default.
- W3119970108 cites W2793165286 @default.
- W3119970108 cites W2805516822 @default.
- W3119970108 cites W2805783416 @default.
- W3119970108 cites W2807401031 @default.
- W3119970108 cites W2810981979 @default.
- W3119970108 cites W2889830342 @default.
- W3119970108 cites W2891977434 @default.
- W3119970108 cites W2898925193 @default.
- W3119970108 cites W2898936689 @default.
- W3119970108 cites W2922281845 @default.
- W3119970108 cites W2962731536 @default.
- W3119970108 cites W2963226019 @default.
- W3119970108 cites W2964105864 @default.
- W3119970108 cites W2964137676 @default.
- W3119970108 cites W2968040091 @default.
- W3119970108 cites W2968557240 @default.
- W3119970108 cites W2970624554 @default.
- W3119970108 doi "https://doi.org/10.1109/iv47402.2020.9304669" @default.
- W3119970108 hasPublicationYear "2020" @default.
- W3119970108 type Work @default.
- W3119970108 sameAs 3119970108 @default.
- W3119970108 citedByCount "0" @default.
- W3119970108 crossrefType "proceedings-article" @default.
- W3119970108 hasAuthorship W3119970108A5012503404 @default.
- W3119970108 hasAuthorship W3119970108A5059792297 @default.
- W3119970108 hasAuthorship W3119970108A5063529163 @default.
- W3119970108 hasAuthorship W3119970108A5083003222 @default.
- W3119970108 hasAuthorship W3119970108A5086523139 @default.
- W3119970108 hasConcept C111919701 @default.
- W3119970108 hasConcept C118505674 @default.
- W3119970108 hasConcept C119857082 @default.
- W3119970108 hasConcept C127313418 @default.
- W3119970108 hasConcept C131979681 @default.
- W3119970108 hasConcept C138885662 @default.
- W3119970108 hasConcept C150899416 @default.
- W3119970108 hasConcept C153180895 @default.
- W3119970108 hasConcept C154945302 @default.
- W3119970108 hasConcept C177264268 @default.
- W3119970108 hasConcept C185592680 @default.
- W3119970108 hasConcept C188027245 @default.
- W3119970108 hasConcept C199360897 @default.
- W3119970108 hasConcept C2776151529 @default.
- W3119970108 hasConcept C2776401178 @default.
- W3119970108 hasConcept C2781238097 @default.
- W3119970108 hasConcept C31972630 @default.
- W3119970108 hasConcept C41008148 @default.
- W3119970108 hasConcept C41895202 @default.
- W3119970108 hasConcept C51399673 @default.
- W3119970108 hasConcept C58489278 @default.
- W3119970108 hasConcept C62649853 @default.
- W3119970108 hasConcept C71139939 @default.
- W3119970108 hasConceptScore W3119970108C111919701 @default.
- W3119970108 hasConceptScore W3119970108C118505674 @default.
- W3119970108 hasConceptScore W3119970108C119857082 @default.
- W3119970108 hasConceptScore W3119970108C127313418 @default.
- W3119970108 hasConceptScore W3119970108C131979681 @default.
- W3119970108 hasConceptScore W3119970108C138885662 @default.
- W3119970108 hasConceptScore W3119970108C150899416 @default.
- W3119970108 hasConceptScore W3119970108C153180895 @default.
- W3119970108 hasConceptScore W3119970108C154945302 @default.
- W3119970108 hasConceptScore W3119970108C177264268 @default.
- W3119970108 hasConceptScore W3119970108C185592680 @default.
- W3119970108 hasConceptScore W3119970108C188027245 @default.
- W3119970108 hasConceptScore W3119970108C199360897 @default.
- W3119970108 hasConceptScore W3119970108C2776151529 @default.
- W3119970108 hasConceptScore W3119970108C2776401178 @default.
- W3119970108 hasConceptScore W3119970108C2781238097 @default.
- W3119970108 hasConceptScore W3119970108C31972630 @default.
- W3119970108 hasConceptScore W3119970108C41008148 @default.
- W3119970108 hasConceptScore W3119970108C41895202 @default.
- W3119970108 hasConceptScore W3119970108C51399673 @default.
- W3119970108 hasConceptScore W3119970108C58489278 @default.
- W3119970108 hasConceptScore W3119970108C62649853 @default.
- W3119970108 hasConceptScore W3119970108C71139939 @default.