{"ID":2885535,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04061","arxiv_id":"2508.04061","title":"TNet: Terrace Convolutional Decoder Network for Remote Sensing Image Semantic Segmentation","abstract":"In remote sensing, most segmentation networks adopt the UNet architecture, often incorporating modules such as Transformers or Mamba to enhance global-local feature interactions within decoder stages. However, these enhancements typically focus on intra-scale relationships and neglect the global contextual dependencies across multiple resolutions. To address this limitation, we introduce the Terrace Convolutional Decoder Network (TNet), a simple yet effective architecture that leverages only convolution and addition operations to progressively integrate low-resolution features (rich in global context) into higher-resolution features (rich in local details) across decoding stages. This progressive fusion enables the model to learn spatially-aware convolutional kernels that naturally blend global and local information in a stage-wise manner. We implement TNet with a ResNet-18 encoder (TNet-R) and evaluate it on three benchmark datasets. TNet-R achieves competitive performance with a mean Intersection-over-Union (mIoU) of 85.35\\% on ISPRS Vaihingen, 87.05\\% on ISPRS Potsdam, and 52.19\\% on LoveDA, while maintaining high computational efficiency. Code is publicly available.","short_abstract":"In remote sensing, most segmentation networks adopt the UNet architecture, often incorporating modules such as Transformers or Mamba to enhance global-local feature interactions within decoder stages. However, these enhancements typically focus on intra-scale relationships and neglect the global contextual dependencies...","url_abs":"https://arxiv.org/abs/2508.04061","url_pdf":"https://arxiv.org/pdf/2508.04061v2","authors":"[\"Chengqian Dai\",\"Yonghong Guo\",\"Hongzhao Xiang\",\"Yigui Luo\"]","published":"2025-08-06T03:44:30Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}