Wu Aming, Han Yahong, Zhu Linchao, Yang Yi
IEEE Trans Pattern Anal Mach Intell. 2022 Aug;44(8):4178-4193. doi: 10.1109/TPAMI.2021.3060446. Epub 2022 Jul 1.
Most state-of-the-art methods of object detection suffer from poor generalization ability when the training and test data are from different domains. To address this problem, previous methods mainly explore to align distribution between source and target domains, which may neglect the impact of the domain-specific information existing in the aligned features. Besides, when transferring detection ability across different domains, it is important to extract the instance-level features that are domain-invariant. To this end, we explore to extract instance-invariant features by disentangling the domain-invariant features from the domain-specific features. Particularly, a progressive disentangled mechanism is proposed to decompose domain-invariant and domain-specific features, which consists of a base disentangled layer and a progressive disentangled layer. Then, with the help of Region Proposal Network (RPN), the instance-invariant features are extracted based on the output of the progressive disentangled layer. Finally, to enhance the disentangled ability, we design a detached optimization to train our model in an end-to-end fashion. Experimental results on four domain-shift scenes show our method is separately 2.3, 3.6, 4.0, and 2.0 percent higher than the baseline method. Meanwhile, visualization analysis demonstrates that our model owns well disentangled ability.
当训练数据和测试数据来自不同领域时，大多数最先进的目标检测方法的泛化能力都很差。为了解决这个问题，以前的方法主要探索对齐源域和目标域之间的分布，这可能会忽略对齐特征中存在的特定领域信息的影响。此外，在跨不同领域转移检测能力时，提取领域不变的实例级特征很重要。为此，我们探索通过从特定领域特征中解缠出领域不变特征来提取实例不变特征。具体来说，提出了一种渐进解缠机制来分解领域不变特征和特定领域特征，它由一个基础解缠层和一个渐进解缠层组成。然后，借助区域提议网络（RPN），基于渐进解缠层的输出提取实例不变特征。最后，为了增强解缠能力，我们设计了一种分离优化方法以端到端的方式训练我们的模型。在四个领域转移场景上的实验结果表明，我们的方法分别比基线方法高2.3%、3.6%、4.0%和2.0%。同时，可视化分析表明我们的模型具有良好的解缠能力。
