论文标题
神经元线性转换：建模人群计数的域移动
Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting
论文作者
论文摘要
跨域人群计数（CDCC）是一个热门话题，因为它在公共安全中的重要性。 CDCC的目的是减轻源和目标域之间的域移位。最近，典型的方法试图通过图像翻译和对抗性学习提取域不变特征。当涉及到特定任务时，我们发现域移位反映在模型参数的差异上。为了直接在参数级别上描述域间隙，我们提出了一种神经元线性变换（NLT）方法，利用域因子和偏置权重以学习域移位。具体而言，对于源模型的特定神经元，NLT利用很少的标记目标数据来学习域移位参数。最后，靶神经元是通过线性转化产生的。与其他域适应方法相比，对六个现实世界数据集进行了广泛的实验和分析，这些数据集验证了NLT的最高性能。一项消融研究还表明，NLT比监督和微调训练更强大，更有效。代码可在：\ url {https://github.com/taohan10200/nlt}中获得。
Cross-domain crowd counting (CDCC) is a hot topic due to its importance in public safety. The purpose of CDCC is to alleviate the domain shift between the source and target domain. Recently, typical methods attempt to extract domain-invariant features via image translation and adversarial learning. When it comes to specific tasks, we find that the domain shifts are reflected on model parameters' differences. To describe the domain gap directly at the parameter-level, we propose a Neuron Linear Transformation (NLT) method, exploiting domain factor and bias weights to learn the domain shift. Specifically, for a specific neuron of a source model, NLT exploits few labeled target data to learn domain shift parameters. Finally, the target neuron is generated via a linear transformation. Extensive experiments and analysis on six real-world datasets validate that NLT achieves top performance compared with other domain adaptation methods. An ablation study also shows that the NLT is robust and more effective than supervised and fine-tune training. Code is available at: \url{https://github.com/taohan10200/NLT}.
