论文标题
改进的规范性卷积用于人群计数
An Improved Normed-Deformable Convolution for Crowd Counting
论文作者
论文摘要
近年来，人群计数已成为计算机视觉中的重要问题。在大多数方法中，密度图是通过从地面图图中与围绕人头中心标记的地面图图的高斯内核来生成的。由于CNN中的固定几何结构和模糊的头尺度信息，因此无法完全获得头部特征。提出了可变形的卷积，以利用头部中CNN特征的比例自适应能力。通过学习采样点的坐标偏移，可以提高调整接受场的能力是可以进行的。但是，头部在可变形卷积中的采样点并不统一，从而导致头部信息丢失。为了处理不均匀的采样，本文提出了通过normed-deformable损失（\ textit {i.e。，} ndloss）实现的改进的规范性的卷积（\ textit {i。，} ndconv）。受NDLOSS限制的采样点的偏移往往更加均匀。然后，更完整地获得了头部中的功能，从而提高性能。尤其是，拟议的NDCONV是一个轻巧的模块，它与可变形的卷积具有相似的计算负担。在广泛的实验中，我们的方法在上海A，Shanghaitech B，UCF \ _QNRF和UCF \ _CC \ _50数据集上优于最先进的方法，分别实现了61.4、7.8、91.2和167.2 Mae。该代码可从https://github.com/bingshuangzhuzi/ndconv获得
In recent years, crowd counting has become an important issue in computer vision. In most methods, the density maps are generated by convolving with a Gaussian kernel from the ground-truth dot maps which are marked around the center of human heads. Due to the fixed geometric structures in CNNs and indistinct head-scale information, the head features are obtained incompletely. Deformable convolution is proposed to exploit the scale-adaptive capabilities for CNN features in the heads. By learning the coordinate offsets of the sampling points, it is tractable to improve the ability to adjust the receptive field. However, the heads are not uniformly covered by the sampling points in the deformable convolution, resulting in loss of head information. To handle the non-uniformed sampling, an improved Normed-Deformable Convolution (\textit{i.e.,}NDConv) implemented by Normed-Deformable loss (\textit{i.e.,}NDloss) is proposed in this paper. The offsets of the sampling points which are constrained by NDloss tend to be more even. Then, the features in the heads are obtained more completely, leading to better performance. Especially, the proposed NDConv is a light-weight module which shares similar computation burden with Deformable Convolution. In the extensive experiments, our method outperforms state-of-the-art methods on ShanghaiTech A, ShanghaiTech B, UCF\_QNRF, and UCF\_CC\_50 dataset, achieving 61.4, 7.8, 91.2, and 167.2 MAE, respectively. The code is available at https://github.com/bingshuangzhuzi/NDConv
