Abstract
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.
Funding Information
  • National Natural Science Foundation of China (62376070, 62206271, 62076195, 12226004, 61721002, 62272375, U20B2052, U22A2029, 12426105)
  • Major Key Project of PCL (PCL2023A08, PCL2024A06)
  • Fundamental Research Funds for the Central Universities (AUGA5710011522)
  • Basic and Applied Basic Research Foundation of Guangdong Province (2020B1515130004)
  • Shenzhen Key Technical Projects (JSGG20220831105801004, CJGJZD2022051714160501)
  • Guangdong University Featured Innovation Program (2024KTSCX026)