Semi-Supervised Counting via Pixel-by-Pixel Density Distribution Modeling
- 21 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (5) , 3625-3638
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.Keywords
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)
This publication has 52 references indexed in Scilit:
- TransCrowd: weakly-supervised crowd counting with transformersScience China Information Sciences, 2022
- Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting2020
- Learning to Count in the Crowd from Limited Labeled Data2020
- Semi-supervised Crowd Counting via Self-training on Surrogate Tasks2020
- Active Crowd Counting with Limited Supervision2020
- Weakly-Supervised Crowd Counting Learns from Sorting Rather Than Locations2020
- End-to-End Object Detection with Transformers2020
- Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds2018
- Scale Aggregation Network for Accurate and Efficient Crowd Counting2018
- Distances and kernels based on cumulative distribution functions2015