crowd counting from unconstrained scene images is a crucial task in many
real-world applications like urban surveillance and management, but it is
greatly challenged by the camera's perspective that causes huge appearance
variations in people's scales and rotations. Conventional method
本文提出了一种新的架构 SPatial Awareness Network (SPANet),并使用 Maximum Excess over Pixels (MEP) loss 来改进目标函数,通过一种多分支的弱监督学习方案来生成具有高差异性的像素级子区域。该框架能够被集成到现有的深度人群计数方法中,是可训练的端到端方法,并在四个具有挑战性的基准测试上进行了广泛的实验,表明我们的方法可以显着提高基线性能,并且在所有基准数据集上优于现有的最先进方法。