<p>Product-type changes in connector manufacturing (e.g., Type-1 to Type-2) often cause a severe domain shift that degrades pixel-level inspection models trained on previous products due to differences in conductor count, spacing, scale, and appearance, even though the underlying conductor structures remain partially shared. Collecting dense segmentation labels for each new product generation is expensive, yet unsupervised domain adaptation (UDA) alone may not meet the high accuracy required for deployment. Therefore, in this paper, we propose a two-stage, label-efficient semi-supervised domain adaptation framework for conductor segmentation under product-type shift. In Stage-1, we initialize the target model from a source-trained segmentation network and perform UDA to reduce the feature gap using unlabeled target data. In Stage-2, we further adapt with a small, labeled target subset and the remaining unlabeled target samples via a teacher–student scheme with confidence-aware pseudo labels and conductor-aware structural priors that suppress noisy regions. Experiments on real connector inspection data show that our method achieves 92.7% mIoU with as little as 3% labeled target data, exceeding the predefined production requirement of 0.9 mIoU, and consistently outperforms one-stage semi-supervised domain adaptation baseline across label budgets. The framework is modular and can be initialized from various UDA/DA checkpoints, making it practical for rapidly evolving production lines.</p>