Tackling background ambiguities in multi-class few-shot point cloud semantic segmentation
Few-shot point cloud semantic segmentation learns to segment novel classes with scarce labeled samples. Within an episode, a novel target class is defined by a few support samples with corresponding binary masks, where only the points of this class are labeled as foreground and others are regarded a...
Saved in:
Main Authors: | Lai, Lvlong, Chen, Jian, Zhang, Chi, Zhang, Zehong, Lin, Guosheng, Wu, Qingyao |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/163370 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Self-regularized prototypical network for few-shot semantic segmentation
by: Ding, Henghui, et al.
Published: (2023) -
FEW-SHOT IMAGE RECOGNITION AND OBJECT DETECTION
by: LI YITING
Published: (2023) -
CRCNet: few-shot segmentation with cross-reference and region–global conditional networks
by: Liu, Weide, et al.
Published: (2023) -
Few-shot vision recognition and generation for the open-world
by: Song, Nan
Published: (2024) -
Few-shot learning in Wi-Fi-based indoor positioning
by: Xie, Feng, et al.
Published: (2024)