Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple annotated source datasets and unlabeled target data to improve the accuracy and robustness of the detection model. Most state-of-the-art MSDA methods for OD perform feature alignment in a class-agnostic manner. This is challenging since the objects have unique modal information due to variations in object appearance across domains. A recent prototype-based approach proposed a class-wise alignment, yet it suffers from error accumulation due to noisy pseudo-labels that can negatively affect adaptation with imbalanced data. To overcome these limitations, we propose an attention-based class-conditioned alignment method for MSDA that aligns instances of each object category across domains. In particular, an attention module coupled with an adversarial domain classifier allows learning domain-invariant and class-specific instance representations. Experimental results on multiple benchmarking MSDA datasets indicate that our method outperforms the state-of-the-art methods and is robust to class imbalance using a conceptually simple class-conditioning method. Our code is available at https://github.com/imatif17/ACIA.

翻译：目标检测的域自适应方法通过促进源域与目标域间的特征对齐来减轻分布偏移的影响。多源域自适应允许利用多个带标注的源数据集和未标注的目标数据，以提高检测模型的准确性和鲁棒性。当前大多数最先进的多源域自适应目标检测方法以类别无关的方式进行特征对齐。由于目标外观在跨域中存在差异，目标具有独特的模态信息，这使得对齐过程具有挑战性。最近一种基于原型的方法提出了逐类对齐，但由于噪声伪标签会导致误差累积，可能对数据不平衡情况下的自适应产生负面影响。为克服这些限制，我们提出了一种基于注意力的类条件对齐方法用于多源域自适应，该方法在跨域中对齐每个目标类别的实例。具体而言，一个注意力模块与对抗性域分类器相结合，能够学习域不变且类别特定的实例表示。在多个基准多源域自适应数据集上的实验结果表明，我们的方法优于现有最先进的方法，并且通过概念简单的类条件方法对类别不平衡具有鲁棒性。我们的代码可在 https://github.com/imatif17/ACIA 获取。