A Pixel-Level Meta-Learner for Weakly Supervised Few-Shot Semantic Segmentation

被引:6
作者
Lee, Yuan-Hao [1 ]
Yang, Fu-En
Wang, Yu-Chiang Frank
机构
[1] Natl Taiwan Univ, Grad Inst Commun Engn, Taipei, Taiwan
来源
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) | 2022年
关键词
D O I
10.1109/WACV51458.2022.00167
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Few-shot semantic segmentation addresses the learning task in which only few images with ground truth pixel-level labels are available for the novel classes of interest. One is typically required to collect a large mount of data (i.e., base classes) with such ground truth information, followed by meta-learning strategies to address the above learning task. When only image-level semantic labels can be observed during both training and testing, it is considered as an even more challenging task of weakly supervised few-shot semantic segmentation. To address this problem, we propose a novel meta-learning framework, which predicts pseudo pixel-level segmentation masks from a limited amount of data and their semantic labels. More importantly, our learning scheme further exploits the produced pixel-level information for query image inputs with segmentation guarantees. Thus, our proposed learning model can be viewed as a pixel-level meta-learner. Through extensive experiments on benchmark datasets, we show that our model achieves satisfactory performances under fully supervised settings, yet performs favorably against state-of-the-art methods under weakly supervised settings.
引用
收藏
页码:1607 / 1617
页数:11
相关论文
共 50 条
[21]   Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation [J].
Tavera, Antonio ;
Cermelli, Fabio ;
Masone, Carlo ;
Caputo, Barbara .
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022), 2022, :1959-1968
[22]   Pseudo-label meta-learner in semi-supervised few-shot learning for remote sensing image scene classification [J].
Miao, Wang ;
Huang, Kai ;
Xu, Zhe ;
Zhang, Jianting ;
Geng, Jie ;
Jiang, Wen .
APPLIED INTELLIGENCE, 2024, 54 (20) :9864-9880
[23]   Generalized Few-shot Semantic Segmentation [J].
Tian, Zhuotao ;
Lai, Xin ;
Jiang, Li ;
Liu, Shu ;
Shu, Michelle ;
Zhao, Hengshuang ;
Jia, Jiaya .
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, :11553-11562
[24]   Optimal Prompting in SAM for Few-Shot and Weakly Supervised Medical Image Segmentation [J].
Siblini, Lara ;
Andrade-Miranda, Gustavo ;
Taguelmimt, Kamilia ;
Visvikis, Dimitris ;
Bert, Julien .
FOUNDATION MODELS FOR GENERAL MEDICAL AI, MEDAGI 2024, 2025, 15184 :103-112
[25]   Pixel-level tunnel crack segmentation using a weakly supervised annotation approach [J].
Wang, Hanxiang ;
Li, Yanfen ;
Dang, L. Minh ;
Lee, Sujin ;
Moon, Hyeonjoon .
COMPUTERS IN INDUSTRY, 2021, 133
[26]   A hybrid approach with optimization-based and metric-based meta-learner for few-shot learning [J].
Wang, Duo ;
Cheng, Yu ;
Yu, Mo ;
Guo, Xiaoxiao ;
Zhang, Tao .
NEUROCOMPUTING, 2019, 349 :202-211
[27]   Learning Pixel-level Semantic Affinity with Image-level Supervision forWeakly Supervised Semantic Segmentation [J].
Ahn, Jiwoon ;
Kwak, Suha .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :4981-4990
[28]   Few-shot Segmentation and Semantic Segmentation for Underwater Imagery [J].
Kabir, Imran ;
Shaurya, Shubham ;
Maigur, Vijayalaxmi ;
Thakurdesai, Nikhil ;
Latnekar, Mahesh ;
Raunak, Mayank ;
Crandall, David ;
Reza, Md Alimoor .
2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2023, :11451-11457
[29]   Learning Meta-class Memory for Few-Shot Semantic Segmentation [J].
Wu, Zhonghua ;
Shi, Xiangxi ;
Lin, Guosheng ;
Cai, Jianfei .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :497-506
[30]   Differentiable Meta-Learning Model for Few-Shot Semantic Segmentation [J].
Tian, Pinzhuo ;
Wu, Zhangkai ;
Qi, Lei ;
Wang, Lei ;
Shi, Yinghuan ;
Gao, Yang .
THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 :12087-12094