Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206133099> ?p ?o ?g. }
- W4206133099 endingPage "3774" @default.
- W4206133099 startingPage "3766" @default.
- W4206133099 abstract "Data augmentation is commonly used to increase the size and diversity of the datasets in machine learning. It is of particular importance to evaluate the robustness of the existing machine learning methods. With progress in geometrical and 3D machine learning, many methods exist to augment a 3D object, from the generation of random orientations to exploring different perspectives of an object. In high-precision applications, the machine learning model must be robust with respect to the small perturbations of the input object. Therefore, there is a need for 3D data augmentation tools that consider the distribution of distance metrics between the original and augmented objects. Here we present Eurecon, the first 3D data augmentation approach with spatial control over the augmented samples. It generates objects uniformly distributed over a sphere with a user-defined radius, which is a distance with respect to the original object. Eurecon is applicable to both point cloud and polygon mesh representations of the 3D objects, as demonstrated on the ModelNet dataset. The method is particularly useful in assessing and improving the machine learning models’ robustness with respect to the transformations of a small magnitude. We demonstrated the superior performance of a point cloud-based model (PointNet++) and a mesh-based model (MeshNet) when trained on datasets augmented with Eurecon, compared to non-augmented and randomly augmented models. Eurecon is computationally efficient, taking ~ 0.1 seconds to generate 1, 000 samples of an object of 1, 000 3D points. Eurecon works with the most common 3D file formats including point cloud and polygon mesh formats." @default.
- W4206133099 created "2022-01-25" @default.
- W4206133099 creator A5011616676 @default.
- W4206133099 creator A5084747952 @default.
- W4206133099 creator A5085541533 @default.
- W4206133099 date "2022-01-01" @default.
- W4206133099 modified "2023-10-18" @default.
- W4206133099 title "Equidistant and Uniform Data Augmentation for 3D Objects" @default.
- W4206133099 cites W1505952289 @default.
- W4206133099 cites W2150066425 @default.
- W4206133099 cites W2211722331 @default.
- W4206133099 cites W2301358467 @default.
- W4206133099 cites W2560609797 @default.
- W4206133099 cites W2585890928 @default.
- W4206133099 cites W2594519801 @default.
- W4206133099 cites W2605102758 @default.
- W4206133099 cites W2748378127 @default.
- W4206133099 cites W2755930428 @default.
- W4206133099 cites W2792124446 @default.
- W4206133099 cites W2795014656 @default.
- W4206133099 cites W2798777114 @default.
- W4206133099 cites W2889300857 @default.
- W4206133099 cites W2902078856 @default.
- W4206133099 cites W2902318384 @default.
- W4206133099 cites W2919853539 @default.
- W4206133099 cites W2943666912 @default.
- W4206133099 cites W2953595166 @default.
- W4206133099 cites W2962731536 @default.
- W4206133099 cites W2962807143 @default.
- W4206133099 cites W2962912205 @default.
- W4206133099 cites W2963108767 @default.
- W4206133099 cites W2963201472 @default.
- W4206133099 cites W2963271314 @default.
- W4206133099 cites W2963727135 @default.
- W4206133099 cites W2965945745 @default.
- W4206133099 cites W2968458129 @default.
- W4206133099 cites W2972423375 @default.
- W4206133099 cites W2972931660 @default.
- W4206133099 cites W2981644170 @default.
- W4206133099 cites W2982319484 @default.
- W4206133099 cites W2988715931 @default.
- W4206133099 cites W3012478585 @default.
- W4206133099 cites W3035424742 @default.
- W4206133099 cites W3097054638 @default.
- W4206133099 cites W3116730076 @default.
- W4206133099 cites W4297598254 @default.
- W4206133099 doi "https://doi.org/10.1109/access.2021.3138162" @default.
- W4206133099 hasPublicationYear "2022" @default.
- W4206133099 type Work @default.
- W4206133099 citedByCount "1" @default.
- W4206133099 countsByYear W42061330992022 @default.
- W4206133099 crossrefType "journal-article" @default.
- W4206133099 hasAuthorship W4206133099A5011616676 @default.
- W4206133099 hasAuthorship W4206133099A5084747952 @default.
- W4206133099 hasAuthorship W4206133099A5085541533 @default.
- W4206133099 hasBestOaLocation W42061330991 @default.
- W4206133099 hasConcept C104317684 @default.
- W4206133099 hasConcept C119857082 @default.
- W4206133099 hasConcept C121684516 @default.
- W4206133099 hasConcept C124101348 @default.
- W4206133099 hasConcept C126042441 @default.
- W4206133099 hasConcept C131979681 @default.
- W4206133099 hasConcept C153715457 @default.
- W4206133099 hasConcept C154945302 @default.
- W4206133099 hasConcept C158245278 @default.
- W4206133099 hasConcept C185592680 @default.
- W4206133099 hasConcept C190694206 @default.
- W4206133099 hasConcept C20894473 @default.
- W4206133099 hasConcept C2524010 @default.
- W4206133099 hasConcept C2781238097 @default.
- W4206133099 hasConcept C31487907 @default.
- W4206133099 hasConcept C31972630 @default.
- W4206133099 hasConcept C33923547 @default.
- W4206133099 hasConcept C41008148 @default.
- W4206133099 hasConcept C55493867 @default.
- W4206133099 hasConcept C63479239 @default.
- W4206133099 hasConcept C64876066 @default.
- W4206133099 hasConcept C76155785 @default.
- W4206133099 hasConceptScore W4206133099C104317684 @default.
- W4206133099 hasConceptScore W4206133099C119857082 @default.
- W4206133099 hasConceptScore W4206133099C121684516 @default.
- W4206133099 hasConceptScore W4206133099C124101348 @default.
- W4206133099 hasConceptScore W4206133099C126042441 @default.
- W4206133099 hasConceptScore W4206133099C131979681 @default.
- W4206133099 hasConceptScore W4206133099C153715457 @default.
- W4206133099 hasConceptScore W4206133099C154945302 @default.
- W4206133099 hasConceptScore W4206133099C158245278 @default.
- W4206133099 hasConceptScore W4206133099C185592680 @default.
- W4206133099 hasConceptScore W4206133099C190694206 @default.
- W4206133099 hasConceptScore W4206133099C20894473 @default.
- W4206133099 hasConceptScore W4206133099C2524010 @default.
- W4206133099 hasConceptScore W4206133099C2781238097 @default.
- W4206133099 hasConceptScore W4206133099C31487907 @default.
- W4206133099 hasConceptScore W4206133099C31972630 @default.
- W4206133099 hasConceptScore W4206133099C33923547 @default.
- W4206133099 hasConceptScore W4206133099C41008148 @default.
- W4206133099 hasConceptScore W4206133099C55493867 @default.
- W4206133099 hasConceptScore W4206133099C63479239 @default.