.png){kind=icon}
返回
Semi-Supervised Few-Shot Classification With Multitask Learning and Iterative Label Correction
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3401071.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Few-shot learning enables rapid generalization from extremely limited training examples. While previous efforts have utilized meta-learning or data augmentation methods to mitigate the problem of data scarcity, such approaches may struggle to maintain robustness and generalize effectively due to overfitting and noise sensitivity. In this article, we propose a novel approach, the semi-supervised label correction method for few-shot learning (SSLC-FSL), which leverages the data distribution of readily available and easily obtainable unlabeled data. SSLC-FSL iteratively corrects the labels of testing samples with alternating steps of pseudo-labeling and sample selection. The objective of pseudo-labeling is to repurpose graph-based semi-supervised learning for joint prediction of the entire testing set. We then introduce a modulation selection network (MSN) to rank testing samples by learning with noisy labels. The training set is expanded by selecting confident pseudo-labeled samples. In the MSN, a modulation aggregation layer is designed to encode support class information into each testing sample, thereby highlighting target category features and mitigating the negative impact of incorrect labels. The iterative label correction process is repeated until all testing samples are recalled to the expanded support set. To boost the SSLC-FSL algorithm, we pretrain a feature extractor to produce general-purpose representations. Particularly, we investigate two types of auxiliary tasks and their collaborative learning to acquire transferable visual information via an end-to-end multitask learning model. Our SSLC-FSL outperforms current state-of-the-art methods in any shot and all data settings, with up to +27.74% on standard remote sensing benchmarks and +5.70% on standard natural scene benchmarks.
Keyword:
Task analysis
Training
Remote sensing
Metalearning
Modulation
Feature extraction
Multitasking
Few-shot learning
modulation aggregation layer (MAL)
modulation selection network (MSN)
multitask learning
semi-supervised learning
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
Efficacy, Safety and Tolerability of Soticlestat (TAK-935/OV935) as an Adjunctive Therapy in Patients with 15q Duplication Syndrome (Dup15q) or Cyclin-Dependent Kinase-Like 5 Deficiency Disorder (CDD) in a Signal-Finding Phase 2 Study (ARCADE) (4096).png)
Neurology
NeurologyIF0
PREAI
分享收藏
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容