AdaCoSeg: Adaptive Shape Co-Segmentation With Group Consistency Loss.

Then, the co-segmentation network iteratively and} jointly optimizes the part labelings across the set subjected to a novel group consistency loss defined by matrix ranks. ... While the part prior network can be trained with noisy and inconsistently segmented shapes, the final output of AdaCoSeg is a consistent part labeling for the input set, with each shape segmented into ... Our main contributions include: • The first DNN for adaptive shape co-segmentation. • A novel and effective group consistency loss based on low-rank approximations. • A co-segmentation training framework ...

arXiv:1903.10297v5 fatcat:kd625cwdqvdfvld6zzfcibucva

Multiple Versions

Then, the co-segmentation network iteratively and jointly optimizes the part labelings across the set subjected to a novel group consistency loss defined by matrix ranks. ... While the part prior network can be trained with noisy and inconsistently segmented shapes, the final output of AdaCoSeg is a consistent part labeling for the input set, with each shape segmented into ... Our main contributions include: • The first DNN for adaptive shape co-segmentation. • A novel and effective group consistency loss based on low-rank approximations. • A co-segmentation training framework ...

doi:10.1109/cvpr42600.2020.00857 dblp:conf/cvpr/0002XCYGZ20 fatcat:7o6j4xxxcregxkvs5yv7o3oo2a

We introduce PartGlot, a neural framework and associated architectures for learning semantic part segmentation of 3D shape geometry, based solely on part referential language. ... Surprisingly, we further demonstrate that the learned part information is generalizable to shape classes unseen during training. ... Low Rank Regularization in AdaCoSeg [46] Table A8 . Results with the group consistency loss introduced by AdaCoSeg [46] . Bold indicates the best result for each column. ...

arXiv:2112.06390v2 fatcat:wvpdbuengjbhphnqfyvzotfvcu

Multiple Versions

This paper provides an in-depth review of recent advancements in DL-based condition monitoring (CM) using 3D PCs, with a specific focus on defect shape classification and segmentation within industrial ... AdaCoSeg takes a set of unsegmented PC shapes as input and iteratively minimizes the group consistency loss to produce shape part labels. ... The authors utilized a voting-based pose estimation algorithm on semantic information of the objects to obtain part segmentation. [195] proposed an adaptive shape co-segmentation (AdaCoSeg) network to ...

arXiv:2402.12923v1 fatcat:v4s7ddpgtffzlg7o4orng7g3zm

Open Access

With reconstruction losses accounted for at each hierarchy level and a decomposition loss at each node, our network training does not require any ground-truth segmentations, let alone hierarchies. ... At each node of the tree, simultaneous feature decoding and shape decomposition are carried out by their respective feature and part decoders, with weight sharing across the same hierarchy level. ... AdaCoSeg [30] learns adaptive co-segmentation over a set of shapes using a group consistency loss. ...

doi:10.48550/arxiv.2201.12763 fatcat:vwfdbbhkubcsljjudejxttciqu

AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss [article]

Preserved Fulltext

Other Versions

AdaCoSeg: Adaptive Shape Co-Segmentation With Group Consistency Loss

Preserved Fulltext

PartGlot: Learning Shape Part Segmentation from Language Reference Games [article]

Preserved Fulltext

Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey [article]

Preserved Fulltext

RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures [article]

Preserved Fulltext