A High-Resolution Remote Sensing Image Building Extraction Model Based on Spectral Index Gated Attention and Transfer Learning

High-resolution remote sensing building extraction often requires large amounts of manually labeled data, and models trained on one dataset may not perform equally well on another without additional annotations. To reduce this dependency on labeled target data, we propose SIGA-UNet3+, which combines a Spectral Index Gated Attention (SIGA) module with a transfer learning strategy. The SIGA module fuses DSBI, NDVI, and NDWI to emphasize building features and suppress vegetation/water interference. Pre-training on the public SpaceNet dataset followed by fine-tuning on a self-built GF-2 dataset (Changchun, China) allows the model to adapt with limited local labels. On SpaceNet, SIGA-UNet3+ achieves F1 = 83.21% and IoU = 70.19%, obtaining the best overall segmentation performance among the compared methods. On the GF-2 dataset, it attains F1 = 84.56% and IoU = 72.17%. Moreover, using only 10% of the GF-2 training samples, transfer learning improves the F1 score by 6–8 percentage points compared to training from scratch. These results indicate that SIGA-UNet3+ can provide a promising and data-efficient approach for high-resolution remote sensing building extraction.