.png){kind=icon}
返回
Crowd Counting Using Meta-Test-Time Adaptation
.png){kind=icon}
PRE
AI
DOI：10.1142/S0129065724500618.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Machine learning algorithms are commonly used for quickly and efficiently counting people from a crowd. Test-time adaptation methods for crowd counting adjust model parameters and employ additional data augmentation to better adapt the model to the specific conditions encountered during testing. The majority of current studies concentrate on unsupervised domain adaptation. These approaches commonly perform hundreds of epochs of training iterations, requiring a sizable number of unannotated data of every new target domain apart from annotated data of the source domain. Unlike these methods, we propose a meta-test-time adaptive crowd counting approach called CrowdTTA, which integrates the concept of test-time adaptation into the meta-learning framework and makes it easier for the counting model to adapt to the unknown test distributions. To facilitate the reliable supervision signal at the pixel level, we introduce uncertainty by inserting the dropout layer into the counting model. The uncertainty is then used to generate valuable pseudo labels, serving as effective supervisory signals for adapting the model. In the context of meta-learning, one image can be regarded as one task for crowd counting. In each iteration, our approach is a dual-level optimization process. In the inner update, we employ a self-supervised consistency loss function to optimize the model so as to simulate the parameters update process that occurs during the test phase. In the outer update, we authentically update the parameters based on the image with ground truth, improving the model's performance and making the pseudo labels more accurate in the next iteration. At test time, the input image is used for adapting the model before testing the image. In comparison to various supervised learning and domain adaptation methods, our results via extensive experiments on diverse datasets showcase the general adaptive capability of our approach across datasets with varying crowd densities and scales.
Keyword:
Crowd counting
meta-learning
test-time adaptation
pseudo labels
dropout
期刊
IF:
6.4
论文数:
1.2K
被引数:
3.3K
机构
引用论文
An approach to reduce vibration and avoid shimmy on landing gears based on an adapted eigenstructure assignment theory.png)
Meccanica
MeccanicaIF0
PREAI
分享收藏
Unsupervised Domain Adaptive Dose Prediction Via Cross-Attention Transformer and Target-Specific Knowledge Preservation基于交叉注意变换器和目标特定知识保存的无监督域自适应剂量预测
OAAI
OAAI分享收藏
查看更多内容