论文标题
在密集场景中人群计数的间接关注点优化
Indirect-Instant Attention Optimization for Crowd Counting in Dense Scenes
论文作者
论文摘要
指导可学习的参数优化的一种吸引人的方法，例如特征图，是全球关注，它以成本的一小部分启发了网络智能。但是，它的损失计算过程仍然很短：1）我们只能产生一维的“伪标签”以供注意，因为该过程中涉及的人工阈值不健壮； 2）等待损失计算的注意力必然是高维的，而通过卷积减少它将不可避免地引入其他可学习的参数，从而使损失的来源感到困惑。为此，我们设计了一个基于软磁性注意的简单但有效的间接注意力优化（IIAO）模块，该模块将高维注意图转换为通过网络中途损耗计算的数学含义的一维特征图，同时自动提供适应性的多尺度融合到功能上的功能模块。特殊转化产生相对粗糙的特征，最初，区域的预测性谬误因人群密度分布而变化，因此我们为区域相关损失（RCLOSS）量身定制以检索连续出现错误的区域和平滑空间信息。广泛的实验证明，我们的方法在许多基准数据集中超过了先前的SOTA方法。
One of appealing approaches to guiding learnable parameter optimization, such as feature maps, is global attention, which enlightens network intelligence at a fraction of the cost. However, its loss calculation process still falls short: 1)We can only produce one-dimensional 'pseudo labels' for attention, since the artificial threshold involved in the procedure is not robust; 2) The attention awaiting loss calculation is necessarily high-dimensional, and decreasing it by convolution will inevitably introduce additional learnable parameters, thus confusing the source of the loss. To this end, we devise a simple but efficient Indirect-Instant Attention Optimization (IIAO) module based on SoftMax-Attention , which transforms high-dimensional attention map into a one-dimensional feature map in the mathematical sense for loss calculation midway through the network, while automatically providing adaptive multi-scale fusion to feature pyramid module. The special transformation yields relatively coarse features and, originally, the predictive fallibility of regions varies by crowd density distribution, so we tailor the Regional Correlation Loss (RCLoss) to retrieve continuous error-prone regions and smooth spatial information . Extensive experiments have proven that our approach surpasses previous SOTA methods in many benchmark datasets.
