Improving the decoding accuracy and information transfer rate (ITR) of steady-state visual evoked potential brain–computer interface (SSVEP-BCI) systems, while enhancing cross-subject generalization and reducing calibration cost, is essential for practical deployment. This study proposes an end-to-end framework that integrates adaptive filtering with semi-supervised domain adaptation. The framework incorporates a Gabor adaptive filter bank (G-AFB) to optimize time–frequency representations and extract features matched to individual neural responses. It also introduces a three-stage semi-supervised domain-adversarial neural network (TriS-DANN), which combines unsupervised pre-alignment and supervised fine-tuning to align cross-subject feature distributions and enable lightweight calibration. On the 1.0 s public benchmark dataset, G-AFB-tCNN achieved 89.13% accuracy, a 4.63 percentage-point improvement over its conventional filter-bank counterpart. On the 0.4 s in-house dataset, G-AFB-tCNN achieved 91.85% accuracy, a 3.22 percentage-point improvement over the conventional fixed filter bank. In transfer learning, TriS-DANN reached 86.60% accuracy using 0.4 s segments extracted from the stimulation period and only 23.07% of the available target-domain training/calibration trials, demonstrating higher efficiency and stability than conventional fine-tuning. These results support the proposed framework as a feasible route toward reliable, low-calibration SSVEP-BCI systems.