GOFENet: A Hybrid Transformer–CNN Network Integrating GEOBIA-Based Object Priors for Semantic Segmentation of Remote Sensing Images

• Published in: Remote sensing (Basel, Switzerland) Vol. 17; no. 15; p. 2652
• Main Authors: He, Tao, Chen, Jianyu, Pan, Delu
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 31.07.2025
• Subjects: Accuracy; Algorithms; Artificial neural networks; Boundaries; Classification; Connectivity; Deep learning; Design; Feature extraction; geographic object-based image analysis; global–local context; Image analysis; Image processing; Image segmentation; Land cover; land cover classification; Machine learning; Modules; multi-scale optimized segmentation; Neural networks; Remote sensing; Representations; Semantic segmentation; Semantics
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs17152652

Geographic object-based image analysis (GEOBIA) has demonstrated substantial utility in remote sensing tasks. However, its integration with deep learning remains largely confined to image-level classification. This is primarily due to the irregular shapes and fragmented boundaries of segmented objects, which limit its applicability in semantic segmentation. While convolutional neural networks (CNNs) excel at local feature extraction, they inherently struggle to capture long-range dependencies. In contrast, Transformer-based models are well suited for global context modeling but often lack fine-grained local detail. To overcome these limitations, we propose GOFENet (Geo-Object Feature Enhanced Network)—a hybrid semantic segmentation architecture that effectively fuses object-level priors into deep feature representations. GOFENet employs a dual-encoder design combining CNN and Swin Transformer architectures, enabling multi-scale feature fusion through skip connections to preserve both local and global semantics. An auxiliary branch incorporating cascaded atrous convolutions is introduced to inject information of segmented objects into the learning process. Furthermore, we develop a cross-channel selection module (CSM) for refined channel-wise attention, a feature enhancement module (FEM) to merge global and local representations, and a shallow–deep feature fusion module (SDFM) to integrate pixel- and object-level cues across scales. Experimental results on the GID and LoveDA datasets demonstrate that GOFENet achieves superior segmentation performance, with 66.02% mIoU and 51.92% mIoU, respectively. The model exhibits strong capability in delineating large-scale land cover features, producing sharper object boundaries and reducing classification noise, while preserving the integrity and discriminability of land cover categories.