.png){kind=icon}
返回
Multi-Task Credible Pseudo-Label Learning for Semi-Supervised Crowd Counting
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2023.3241211.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As a widely used semi-supervised learning strategy, self-training generates pseudo-labels to alleviate the labor-intensive and time-consuming annotation problems in crowd counting while boosting the model performance with limited labeled data and massive unlabeled data. However, the noise in the pseudo-labels of the density maps greatly hinders the performance of semi-supervised crowd counting. Although auxiliary tasks, e.g., binary segmentation, are utilized to help improve the feature representation learning ability, they are isolated from the main task, i.e., density map regression and the multi-task relationships are totally ignored. To address the above issues, we develop a multi-task credible pseudo-label learning (MTCP) framework for crowd counting, consisting of three multi-task branches, i.e., density regression as the main task, and binary segmentation and confidence prediction as the auxiliary tasks. Multi-task learning is conducted on the labeled data by sharing the same feature extractor for all three tasks and taking multi-task relations into account. To reduce epistemic uncertainty, the labeled data are further expanded, by trimming the labeled data according to the predicted confidence map for low-confidence regions, which can be regarded as an effective data augmentation strategy. For unlabeled data, compared with the existing works that only use the pseudo-labels of binary segmentation, we generate credible pseudo-labels of density maps directly, which can reduce the noise in pseudo-labels and therefore decrease aleatoric uncertainty. Extensive comparisons on four crowd-counting datasets demonstrate the superiority of our proposed model over the competing methods. The code is available at: https://github.com/ljq2000/MTCP.
Keyword:
Task analysis
Uncertainty
Multitasking
Data models
Predictive models
Feature extraction
Semisupervised learning
Crowd counting
multi-task learning
self-training
semi-supervised
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Innovation, creativity and governance: Social dynamics of economic performance in city-regions.png)
Innovation
InnovationIF0
PREAI
分享收藏Crystalline‐State Reaction with Allosteric Effect in Spin‐Crossover, Interpenetrated Networks with Magnetic and Optical Bistability具有磁和光学双稳态的自旋交叉，互穿网络中具有变构效应的晶态反应
PREAI
分享收藏分享收藏分享收藏Counting Crowd by Weighing Counts: A Sequential Decision-Making Perspective通过称重计数来计数人群: 顺序决策的观点
PREAI
分享收藏
查看更多内容