论文标题
像人类一样计算：类人群人群依靠建模对象的相似性
Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects
论文作者
论文摘要
主流人群计数方法会回归密度图并集成得分以获得计数结果。由于密度表示与其相邻分布相关，因此它嵌入具有变异值的相同类别对象，而人类计算模型的模型不变特征，即与对象相似。受此启发的启发，我们提出了一个理性和人为人群计数框架的框架。首先，我们利用计数标量为监督信号，该信号为类似事项提供了全球和隐性的指导。然后，大型内核CNN被用来模仿人类的范式，该范式首先模拟不变知识并幻灯片以比较相似性。后来，提出了对预训练的并行参数的重新参数化，以迎合相似性比较的内阶段差异。最后，提出了随机缩放贴片的产量（RSY），以促进长距离依赖性的相似性建模。对人群计数中五个具有挑战性的基准测试的广泛实验表明，所提出的框架实现了最先进的框架。
The mainstream crowd counting methods regress density map and integrate it to obtain counting results. Since the density representation to one head accords to its adjacent distribution, it embeds the same category objects with variant values, while human beings counting models the invariant features namely similarity to objects. Inspired by this, we propose a rational and anthropoid crowd counting framework. To begin with, we leverage counting scalar as supervision signal, which provides global and implicit guidance to similar matters. Then, the large kernel CNN is utilized to imitate the paradigm of human beings which models invariant knowledge firstly and slides to compare similarity. Later, re-parameterization on pre-trained paralleled parameters is presented to cater to the inner-class variance on similarity comparison. Finally, the Random Scaling patches Yield (RSY) is proposed to facilitate similarity modeling on long distance dependencies. Extensive experiments on five challenging benchmarks in crowd counting show the proposed framework achieves state-of-the-art.
