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: | , , , , , |
---|---|
Other Authors: | |
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 |
id |
sg-ntu-dr.10356-163370 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1633702022-12-05T03:35:46Z Tackling background ambiguities in multi-class few-shot point cloud semantic segmentation Lai, Lvlong Chen, Jian Zhang, Chi Zhang, Zehong Lin, Guosheng Wu, Qingyao School of Computer Science and Engineering Engineering::Computer science and engineering Few-Shot Point Cloud 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 as background. In the tasks involving multiple target classes, since the meanings of background are diverse for different target classes, background ambiguities appear: Some points labeled as background in one support sample may be of other target classes. It will result in incorrect guidance and damage model's segmentation performance. However, previous methods in the literature do not consider this problem. In this paper, we propose a simple yet effective approach to tackle background ambiguities, which adopts the entropy of predictions on query samples to the training objective function as an additional regularization. Besides, we design a feature transformation operation to reduce the feature differences between support and query samples. With our proposed approach, fine-tuning, a weak baseline method for few-shot segmentation, gains significant performance improvement (e.g., 7.48% and 7.04% in 2-way-1-shot and 3-way-1-shot tasks of S3DIS, respectively) and outperforms current state-of-the-art methods in all the task settings of S3DIS and ScanNet benchmark datasets. Ministry of Education (MOE) National Research Foundation (NRF) This work was supported by National Natural Science Foundation of China (NSFC) 61876208, Tip-top Scientific and Technical Innovative Youth Talents of Guangdong Special Support Program (2019TQ05X200), 2022 Tencent Wechat Rhino-Bird Focused Research Program Research (Tencent WeChat RBFR2022008) and the National Research Foundation, Singapore under its AI Singapore Programme (AISG Award No: AISG-RP-2018-003), the Ministry of Education, Singapore, under its Academic Research Fund Tier 2 (MOE-T2EP20220-0007) and Tier 1 (RG95/20). 2022-12-05T03:35:46Z 2022-12-05T03:35:46Z 2022 Journal Article Lai, L., Chen, J., Zhang, C., Zhang, Z., Lin, G. & Wu, Q. (2022). Tackling background ambiguities in multi-class few-shot point cloud semantic segmentation. Knowledge-Based Systems, 253, 109508-. https://dx.doi.org/10.1016/j.knosys.2022.109508 0950-7051 https://hdl.handle.net/10356/163370 10.1016/j.knosys.2022.109508 2-s2.0-85135539483 253 109508 en MOE-T2EP20220-0007 RG95/20 AISG-RP-2018-003 Knowledge-Based Systems © 2022 Elsevier B.V. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Few-Shot Point Cloud |
spellingShingle |
Engineering::Computer science and engineering Few-Shot Point Cloud Lai, Lvlong Chen, Jian Zhang, Chi Zhang, Zehong Lin, Guosheng Wu, Qingyao Tackling background ambiguities in multi-class few-shot point cloud semantic segmentation |
description |
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 as background. In the tasks involving multiple target classes, since the meanings of background are diverse for different target classes, background ambiguities appear: Some points labeled as background in one support sample may be of other target classes. It will result in incorrect guidance and damage model's segmentation performance. However, previous methods in the literature do not consider this problem. In this paper, we propose a simple yet effective approach to tackle background ambiguities, which adopts the entropy of predictions on query samples to the training objective function as an additional regularization. Besides, we design a feature transformation operation to reduce the feature differences between support and query samples. With our proposed approach, fine-tuning, a weak baseline method for few-shot segmentation, gains significant performance improvement (e.g., 7.48% and 7.04% in 2-way-1-shot and 3-way-1-shot tasks of S3DIS, respectively) and outperforms current state-of-the-art methods in all the task settings of S3DIS and ScanNet benchmark datasets. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Lai, Lvlong Chen, Jian Zhang, Chi Zhang, Zehong Lin, Guosheng Wu, Qingyao |
format |
Article |
author |
Lai, Lvlong Chen, Jian Zhang, Chi Zhang, Zehong Lin, Guosheng Wu, Qingyao |
author_sort |
Lai, Lvlong |
title |
Tackling background ambiguities in multi-class few-shot point cloud semantic segmentation |
title_short |
Tackling background ambiguities in multi-class few-shot point cloud semantic segmentation |
title_full |
Tackling background ambiguities in multi-class few-shot point cloud semantic segmentation |
title_fullStr |
Tackling background ambiguities in multi-class few-shot point cloud semantic segmentation |
title_full_unstemmed |
Tackling background ambiguities in multi-class few-shot point cloud semantic segmentation |
title_sort |
tackling background ambiguities in multi-class few-shot point cloud semantic segmentation |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/163370 |
_version_ |
1751548591516680192 |