Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034652543> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3034652543 abstract "Recently, deep neural networks are introduced as supervised discriminative models for the learning of 3D point cloud segmentation. Most previous supervised methods require a large number of training data with human annotation part labels to guide the training process to ensure the model's generalization abilities on test data. In comparison, we propose a novel 3D shape segmentation method that requires few labeled data for training. Given an input 3D shape, the training of our model starts with identifying a similar 3D shape with part annotations from a mini-pool of shape templates (e.g. 10 shapes). With the selected template shape, a novel Coherent Point Transformer is proposed to fully leverage the power of a deep neural network to smoothly morph the template shape towards the input shape. Then, based on the transformed template shapes with part labels, a newly proposed Part-specific Density Estimator is developed to learn a continuous part-specific probability distribution function on the entire 3D space with a batch consistency regularization term. With the learned part-specific probability distribution, our model is able to predict the part labels of a new input 3D shape in an end-to-end manner. We demonstrate that our proposed method can achieve remarkable segmentation results on the ShapeNet dataset with few shots, compared to previous supervised learning approaches." @default.
- W3034652543 created "2020-06-19" @default.
- W3034652543 creator A5034116108 @default.
- W3034652543 creator A5081971554 @default.
- W3034652543 creator A5083935587 @default.
- W3034652543 date "2020-06-01" @default.
- W3034652543 modified "2023-10-12" @default.
- W3034652543 title "Few-Shot Learning of Part-Specific Probability Space for 3D Shape Segmentation" @default.
- W3034652543 cites W1644641054 @default.
- W3034652543 cites W1989540182 @default.
- W3034652543 cites W2003940193 @default.
- W3034652543 cites W2010209818 @default.
- W3034652543 cites W2028950582 @default.
- W3034652543 cites W2053008628 @default.
- W3034652543 cites W2103837466 @default.
- W3034652543 cites W2277007198 @default.
- W3034652543 cites W2560722161 @default.
- W3034652543 cites W2565662353 @default.
- W3034652543 cites W2765901044 @default.
- W3034652543 cites W2788158258 @default.
- W3034652543 cites W2796426482 @default.
- W3034652543 cites W2893477965 @default.
- W3034652543 cites W2897035133 @default.
- W3034652543 cites W2946653762 @default.
- W3034652543 cites W2962731536 @default.
- W3034652543 cites W2963231572 @default.
- W3034652543 cites W2963719584 @default.
- W3034652543 cites W2963727135 @default.
- W3034652543 cites W2982590312 @default.
- W3034652543 cites W2986782335 @default.
- W3034652543 cites W3004739592 @default.
- W3034652543 cites W3008274274 @default.
- W3034652543 cites W3009841631 @default.
- W3034652543 cites W3104141662 @default.
- W3034652543 doi "https://doi.org/10.1109/cvpr42600.2020.00456" @default.
- W3034652543 hasPublicationYear "2020" @default.
- W3034652543 type Work @default.
- W3034652543 sameAs 3034652543 @default.
- W3034652543 citedByCount "18" @default.
- W3034652543 countsByYear W30346525432020 @default.
- W3034652543 countsByYear W30346525432021 @default.
- W3034652543 countsByYear W30346525432022 @default.
- W3034652543 countsByYear W30346525432023 @default.
- W3034652543 crossrefType "proceedings-article" @default.
- W3034652543 hasAuthorship W3034652543A5034116108 @default.
- W3034652543 hasAuthorship W3034652543A5081971554 @default.
- W3034652543 hasAuthorship W3034652543A5083935587 @default.
- W3034652543 hasConcept C111919701 @default.
- W3034652543 hasConcept C124504099 @default.
- W3034652543 hasConcept C153180895 @default.
- W3034652543 hasConcept C154945302 @default.
- W3034652543 hasConcept C191897082 @default.
- W3034652543 hasConcept C192562407 @default.
- W3034652543 hasConcept C2778344882 @default.
- W3034652543 hasConcept C2778572836 @default.
- W3034652543 hasConcept C31972630 @default.
- W3034652543 hasConcept C41008148 @default.
- W3034652543 hasConcept C89600930 @default.
- W3034652543 hasConceptScore W3034652543C111919701 @default.
- W3034652543 hasConceptScore W3034652543C124504099 @default.
- W3034652543 hasConceptScore W3034652543C153180895 @default.
- W3034652543 hasConceptScore W3034652543C154945302 @default.
- W3034652543 hasConceptScore W3034652543C191897082 @default.
- W3034652543 hasConceptScore W3034652543C192562407 @default.
- W3034652543 hasConceptScore W3034652543C2778344882 @default.
- W3034652543 hasConceptScore W3034652543C2778572836 @default.
- W3034652543 hasConceptScore W3034652543C31972630 @default.
- W3034652543 hasConceptScore W3034652543C41008148 @default.
- W3034652543 hasConceptScore W3034652543C89600930 @default.
- W3034652543 hasLocation W30346525431 @default.
- W3034652543 hasOpenAccess W3034652543 @default.
- W3034652543 hasPrimaryLocation W30346525431 @default.
- W3034652543 hasRelatedWork W1669643531 @default.
- W3034652543 hasRelatedWork W1721780360 @default.
- W3034652543 hasRelatedWork W2110230079 @default.
- W3034652543 hasRelatedWork W2117664411 @default.
- W3034652543 hasRelatedWork W2117933325 @default.
- W3034652543 hasRelatedWork W2122581818 @default.
- W3034652543 hasRelatedWork W2159066190 @default.
- W3034652543 hasRelatedWork W2739874619 @default.
- W3034652543 hasRelatedWork W2965422042 @default.
- W3034652543 hasRelatedWork W1967061043 @default.
- W3034652543 isParatext "false" @default.
- W3034652543 isRetracted "false" @default.
- W3034652543 magId "3034652543" @default.
- W3034652543 workType "article" @default.