Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling
ICLR 2023(2024)
摘要
This paper focuses on semi-supervised crowd counting, where only a small
portion of the training data are labeled. We formulate the pixel-wise density
value to regress as a probability distribution, instead of a single
deterministic value. On this basis, we propose a semi-supervised crowd-counting
model. Firstly, we design a pixel-wise distribution matching loss to measure
the differences in the pixel-wise density distributions between the prediction
and the ground truth; Secondly, we enhance the transformer decoder by using
density tokens to specialize the forwards of decoders w.r.t. different density
intervals; Thirdly, we design the interleaving consistency self-supervised
learning mechanism to learn from unlabeled data efficiently. Extensive
experiments on four datasets are performed to show that our method clearly
outperforms the competitors by a large margin under various labeled ratio
settings. Code will be released at
https://github.com/LoraLinH/Semi-supervised-Counting-via-Pixel-by-pixel-Density-Distribution-Modelling.
更多查看译文
关键词
Computer Vision,Crowd Counting,Semi-Supervised Learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要