论文标题
NAS计数：与神经架构搜索进行计数
NAS-Count: Counting-by-Density with Neural Architecture Search
论文作者
论文摘要
人群计数的最新进展大部分都是从手工设计的密度估计网络演变而来的，在该网络中，多尺度功能被利用以解决规模变化问题，但以苛刻的设计工作为代价。在这项工作中，我们使用神经体系结构搜索（NAS）自动化计数模型的设计，并引入端到端搜索的编码器架构，自动多尺度网络（AMSNET）。具体而言，我们利用了特定于计数的两级搜索空间。 AMSNET中的编码器和解码器由从微观搜索中发现的不同单元组成，而通过宏观搜索探索了多路径体系结构。为了解决MSE损失中的像素级隔离问题，AMSNET通过自动搜索的量表金字塔池损失（SPPLOSS）进行了优化，该损失（SPPLOSS）监督了多尺度的结构信息。四个数据集上的广泛实验显示AMSNET产生的最新结果，表现优于手工设计的模型，完全证明了NAS计数的功效。
Most of the recent advances in crowd counting have evolved from hand-designed density estimation networks, where multi-scale features are leveraged to address the scale variation problem, but at the expense of demanding design efforts. In this work, we automate the design of counting models with Neural Architecture Search (NAS) and introduce an end-to-end searched encoder-decoder architecture, Automatic Multi-Scale Network (AMSNet). Specifically, we utilize a counting-specific two-level search space. The encoder and decoder in AMSNet are composed of different cells discovered from micro-level search, while the multi-path architecture is explored through macro-level search. To solve the pixel-level isolation issue in MSE loss, AMSNet is optimized with an auto-searched Scale Pyramid Pooling Loss (SPPLoss) that supervises the multi-scale structural information. Extensive experiments on four datasets show AMSNet produces state-of-the-art results that outperform hand-designed models, fully demonstrating the efficacy of NAS-Count.
