IEEE Trans Neural Netw Learn Syst. 2022 Aug;33(8):3238-3250. doi: 10.1109/TNNLS.2021.3051371. Epub 2022 Aug 3.
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 in 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 data sets 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 https://github.com/taohan10200/NLT.
跨领域人群计数 (CDCC) 因其在公共安全中的重要性而成为热门话题。CDCC 的目的是减轻源域和目标域之间的域偏移。最近，典型的方法试图通过图像转换和对抗性学习来提取域不变特征。在具体任务中，我们发现域偏移反映在模型参数的差异上。为了直接在参数级别描述域间隙，我们提出了一种神经元线性变换 (NLT) 方法，利用域因子和偏差权重来学习域偏移。具体来说，对于源模型的特定神经元，NLT 利用少量有标签的目标数据来学习域偏移参数。最后，通过线性变换生成目标神经元。在六个真实数据集上的广泛实验和分析验证了 NLT 与其他域自适应方法相比具有最佳性能。消融研究还表明，NLT 比监督训练和微调训练更稳健、更有效。代码可在 https://github.com/taohan10200/NLT 获得。
