|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM380139634 |
| 003 |
DE-627 |
| 005 |
20250306215435.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
241115s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2024.3496670
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1266.xml
|
| 035 |
|
|
|a (DE-627)NLM380139634
|
| 035 |
|
|
|a (NLM)39527440
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wei, Xin
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Multi-scale Part-based Feature Representation for 3D Domain Generalization and Adaptation
|
| 264 |
|
1 |
|c 2024
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 11.11.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status Publisher
|
| 520 |
|
|
|a Deep networks on 3D point clouds have achieved remarkable success in 3D classification, but they are vulnerable to geometric variations resulting from inconsistent data acquisition procedures. This leads to challenging 3D domain generalization and adaptation tasks, aiming to tackle the challenge that the performance of a model trained on a source domain will degrade on an out-of-distribution target domain. In this paper, we introduce a novel Multi-Scale Part-based feature Representation, dubbed MSPR, as a generalizable representation for point cloud domain generalization and adaptation. Rather than relying on the global point cloud feature representation, we align the part-level features of shapes at different scales to a set of learnable part-template features, which can encode local geometric structures shared between the source and the target domains. Specifically, we construct a part-template feature space shared between source and target domains. Shapes from different domains are organized into part-level features at various scales and then aligned to the part-template features. To leverage the generalization ability of small-scale parts and the discrimination ability of large-scale parts, we further design a cross-scale feature fusion module to exchange information between aligned part-based features at different scales. The fused part-based representations are finally aggregated by a part-based feature aggregation module. To improve the robustness of the aligned part-based representations and global shape representation to geometry variations, we further propose a Contrastive Learning framework on Shape Representation (CLSR), applied to both 3D domain generalization and adaptation tasks. We conduct experiments on 3D domain generalization and adaptation benchmarks for point cloud classification. Experimental results demonstrate the effectiveness of our proposed approach, outperforming the previous state-of-the-art methods for both domain generalization and adaptation tasks. Ablation studies confirm the effectiveness of the proposed components in our model
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Gu, Xiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Sun, Jian
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g PP(2024) vom: 11. Nov.
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnas
|
| 773 |
1 |
8 |
|g volume:PP
|g year:2024
|g day:11
|g month:11
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3496670
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d PP
|j 2024
|b 11
|c 11
|