Detecting defects in printed labels is essential for quality control. Although a few vision-based models have been proposed for this challenging task, they fail to deal with the large deformation in printed labels and cannot be generalized well to unseen defects. To this end, we propose a novel triple-stream Siamese segmentation network (TSS-Net) to overcome these issues. TSS-Net utilizes two separate Siamese groups integrated with a registration module (RM) to learn differential features based on Siamese similarity comparison and employs a feature complementary learning strategy, so that the model can simultaneously handle large deformations and generalize to unseen defects. Specifically, a pretrained RM is integrated into the TSS-Net to achieve end-to-end detection, which enhances the robustness to large deformations. Moreover, a group of differential feature enhancement (DFE) modules are constructed to learn differential features at different scales, which forces the network to focus on changed features while ignoring invariant features. Further, a feature complementary learning strategy is designed to fuse differential features at different scales, which can suppress artifacts during network reconstruction. Finally, a method is proposed to simulate printed labels with varying degrees of deformation and artificial defects. Extensive experimental results show that our proposed TSS-Net yields the best performance compared with the state-of-the-art method. Specifically, our proposed method achieves improvements of 4.20% on the $F_{1}$ score and 7.51% on the intersection over union (IoU).