基于逐像素密度分布建模的半监督计数
Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling
AI总结：
本文针对半监督人群计数问题，提出将逐像素密度建模为概率分布，并结合分布匹配损失、密度令牌增强解码器及交错一致性自监督机制，在多个数据集上显著超越现有方法。
摘要：
本文聚焦于半监督人群计数，其中仅有一小部分训练数据带有标注。我们将待回归的逐像素密度值建模为概率分布，而非单一的确定性数值。在此基础上，提出了一种半监督人群计数模型。首先，设计了一种逐像素分布匹配损失，用于衡量预测与真值之间逐像素密度分布的差异；其次，通过使用密度令牌增强Transformer解码器，使解码器的前向过程针对不同密度区间进行专门化处理；第三，设计了交错一致性自监督学习机制，以高效地从无标注数据中学习。在四个数据集上进行了大量实验，结果表明，在各种标注比例设置下，我们的方法均以较大幅度明显优于竞争对手。代码将发布在 https://github.com/LoraLinH/Semi-supervised-Counting-via-Pixel-by-pixel-Density-Distribution-Modelling。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
