Multi-scale pseudo-labels filtering and key pixels adversarial alignment for domain adaptive object detection

Domain Adaptive Object Detection (DAOD) aims to adapt a detector trained on the labeled source domain to perform effectively on the unlabeled target domain. Most existing DAOD methods commonly employ self-training strategy and adversarial learning. However, the methods based on the self-training strategy often generate unreliable pseudo-labels (e.g., missing detections and false positives) due to the absence of target domain semantics, resulting in suboptimal models. Meanwhile, aligning a large number of unimportant pixels hampers adversarial learning’s ability to capture domain-invariant semantic information. Therefore, we propose the Multi-scale Adversarial Teacher Framework (MATF) based on the common self-training framework (teacher–student framework). Specifically, to mitigate the impact of unreliable pseudo-labels, we propose the Multi-scale Negatives Filtering (MNF) module in the teacher model, which prevents missing detections from damaging the model by filtering out unreliable negative samples at multiple feature scales. In addition, we propose the Multi-scale Key-Pixel Discriminator (MKPD), which predicts the distributions of key pixels at multiple feature scales emphasizing the adversarial alignment of key pixels rather than unimportant pixels. Finally, to generate higher-quality pseudo-labels, we introduce the discriminator into the student model to reduce the model’s bias towards the source domain. Unlike most methods, we construct our method on a computationally efficient but less work-intensive one-stage detector. Extensive experiments conducted on DAOD benchmark datasets such as Cityscapes, FoggyCityscapes, KITTI, and Sim10k demonstrate the strong adaptability and effectiveness of MATF.