像素
人工智能
计算机科学
计算机视觉
模式识别(心理学)
分布(数学)
数学
数学分析
作者
Hui Lin,Zhiheng Ma,Rongrong Ji,Yaowei Wang,Zhou Su,Xiaopeng Hong,Deyu Meng
标识
DOI:10.1109/tpami.2025.3532512
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. First, 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; Second, we enhance the transformer decoder by using density tokens to specialize the forwards of decoders w.r.t. different density intervals; Third, 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.
科研通智能强力驱动
Strongly Powered by AbleSci AI