{"ID":2825636,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.19990","arxiv_id":"2512.19990","title":"A Dual-Branch Local-Global Framework for Cross-Resolution Land Cover Mapping","abstract":"Cross-resolution land cover mapping aims to produce high-resolution semantic predictions from coarse or low-resolution supervision, yet the severe resolution mismatch makes effective learning highly challenging. Existing weakly supervised approaches often struggle to align fine-grained spatial structures with coarse labels, leading to noisy supervision and degraded mapping accuracy. To tackle this problem, we propose DDTM, a dual-branch weakly supervised framework that explicitly decouples local semantic refinement from global contextual reasoning. Specifically, DDTM introduces a diffusion-based branch to progressively refine fine-scale local semantics under coarse supervision, while a transformer-based branch enforces long-range contextual consistency across large spatial extents. In addition, we design a pseudo-label confidence evaluation module to mitigate noise induced by cross-resolution inconsistencies and to selectively exploit reliable supervisory signals. Extensive experiments demonstrate that DDTM establishes a new state-of-the-art on the Chesapeake Bay benchmark, achieving 66.52\\% mIoU and substantially outperforming prior weakly supervised methods. The code is available at https://github.com/gpgpgp123/DDTM.","short_abstract":"Cross-resolution land cover mapping aims to produce high-resolution semantic predictions from coarse or low-resolution supervision, yet the severe resolution mismatch makes effective learning highly challenging. Existing weakly supervised approaches often struggle to align fine-grained spatial structures with coarse la...","url_abs":"https://arxiv.org/abs/2512.19990","url_pdf":"https://arxiv.org/pdf/2512.19990v1","authors":"[\"Peng Gao\",\"Ke Li\",\"Di Wang\",\"Yongshan Zhu\",\"Yiming Zhang\",\"Xuemei Luo\",\"Yifeng Wang\"]","published":"2025-12-23T02:32:02Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false,"code_links":[{"ID":605685,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2825636,"paper_url":"https://arxiv.org/abs/2512.19990","paper_title":"A Dual-Branch Local-Global Framework for Cross-Resolution Land Cover Mapping","repo_url":"https://github.com/gpgpgp123/DDTM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}