.png){kind=icon}
返回
Semi-Supervised Crowd Counting via Multiple Representation Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2023.3313490.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
There has been a growing interest in counting crowds through computer vision and machine learning techniques in recent years. Despite that significant progress has been made, most existing methods heavily rely on fully-supervised learning and require a lot of labeled data. To alleviate the reliance, we focus on the semi-supervised learning paradigm. Usually, crowd counting is converted to a density estimation problem. The model is trained to predict a density map and obtains the total count by accumulating densities over all the locations. In particular, we find that there could be multiple density map representations for a given image in a way that they differ in probability distribution forms but reach a consensus on their total counts. Therefore, we propose multiple representation learning to train several models. Each model focuses on a specific density representation and utilizes the count consistency between models to supervise unlabeled data. To bypass the explicit density regression problem, which makes a strong parametric assumption on the underlying density distribution, we propose an implicit density representation method based on the kernel mean embedding. Extensive experiments demonstrate that our approach outperforms state-of-the-art semi-supervised methods significantly.
Keyword:
Crowd counting
semi-supervised learning
kernel mean embedding
reproducing kernel Hilbert space
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
.png){kind=icon}
Symplectic Principal Component Analysis: A New Method for Time Series Analysis辛主成分分析: 一种新的时间序列分析方法
OAAI
OAAI分享收藏分享收藏
查看更多内容