|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM376547367 |
| 003 |
DE-627 |
| 005 |
20241108232410.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240822s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2024.3447008
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1594.xml
|
| 035 |
|
|
|a (DE-627)NLM376547367
|
| 035 |
|
|
|a (NLM)39167501
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Xie, Tao
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a CO-Net++
|b A Cohesive Network for Multiple Point Cloud Tasks at Once With Two-Stage Feature Rectification
|
| 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 08.11.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a We present CO-Net++, a cohesive framework that optimizes multiple point cloud tasks collectively across heterogeneous dataset domains with a two-stage feature rectification strategy. The core of CO-Net++ lies in optimizing task-shared parameters to capture universal features across various tasks while discerning task-specific parameters tailored to encapsulate the unique characteristics of each task. Specifically, CO-Net++ develops a two-stage feature rectification strategy (TFRS) that distinctly separates the optimization processes for task-shared and task-specific parameters. At the first stage, TFRS configures all parameters in backbone as task-shared, which encourages CO-Net++ to thoroughly assimilate universal attributes pertinent to all tasks. In addition, TFRS introduces a sign-based gradient surgery to facilitate the optimization of task-shared parameters, thus alleviating conflicting gradients induced by various dataset domains. In the second stage, TFRS freezes task-shared parameters and flexibly integrates task-specific parameters into the network for encoding specific characteristics of each dataset domain. CO-Net++ prominently mitigates conflicting optimization caused by parameter entanglement, ensuring the sufficient identification of universal and specific features. Extensive experiments reveal that CO-Net++ realizes exceptional performances on both 3D object detection and 3D semantic segmentation tasks. Moreover, CO-Net++ delivers an impressive incremental learning capability and prevents catastrophic amnesia when generalizing to new point cloud tasks
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Dai, Kun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Sun, Qihao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jiang, Zhiqiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Cao, Chuqing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhao, Lijun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Ke
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Ruifeng
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 46(2024), 12 vom: 01. Nov., Seite 10911-10928
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:12
|g day:01
|g month:11
|g pages:10911-10928
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3447008
|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 46
|j 2024
|e 12
|b 01
|c 11
|h 10911-10928
|