{"type":"ScholarlyArticle","title":"Coarse-to-Fine Domain Incremental Learning with Attentive Distillation for Mining Footprint Segmentation in Multispectral Imagery","authors":[{"name":"Alif Tri Handoyo","slug":"alif-tri-handoyo","given":"Alif Tri","family":"Handoyo","affiliation":""},{"name":"Vincent C.S. Lee","slug":"vincent-c-s-lee","given":"Vincent C.S.","family":"Lee","affiliation":""},{"name":"Rizka Widyarini Purwanto","slug":"rizka-widyarini-purwanto","given":"Rizka Widyarini","family":"Purwanto","affiliation":""},{"name":"Alex M. Lechner","slug":"alex-m-lechner","given":"Alex M.","family":"Lechner","affiliation":""},{"name":"Deanna Kemp","slug":"deanna-kemp","given":"Deanna","family":"Kemp","affiliation":""},{"name":"Muhamad Risqi U. Saputra","slug":"muhamad-risqi-u-saputra","given":"Muhamad Risqi U.","family":"Saputra","affiliation":""}],"abstract":"Automatically mapping and segmenting global mining footprints using remote sensing and deep learning is critical for monitoring the socio-environmental risks and impacts of mining, yet its progress is hindered by the scarcity of fine-grained annotated data. Although large-scale datasets with coarse boundaries are widely available, leveraging them to improve fine-grained segmentation is challenging due to significant domain shift. To address this, we propose MineC2FNet, a coarse-to-fine domain incremental learning framework that exploits abundant coarse data to enhance fine-grained mining footprint segmentation. MineC2FNet adopts a teacher–student architecture with attentive distillation at both the feature and prediction levels, selectively transferring generalized knowledge from the coarse domain while enabling boundary refinement using limited fine-grained data (fine domain). We further introduce an expertly validated dataset of 219 images with precise boundary annotations across diverse geographies and commodities. Extensive experiments against state-of-the-art approaches, including domain adaptation and domain incremental learning methods, demonstrate that MineC2FNet achieves superior performance while effectively handling domain shift. The dataset and code are publicly available at https://github.com/risqiutama/MineC2FNet.","doi":"10.24963/ijcai.2026/800","url":"https://ijcai.org/proceedings/2026/800","pdf":"https://ijcai.org/proceedings/2026/0800.pdf","markdown":"https://ijcai.org/proceedings/2026/800.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/800","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI and Social Good","track":"AI and Social Good","number":800,"pages":{"first":7192,"last":7200},"keywords":["AI4G: Multidisciplinary Topics and Applications","AI4G: Computer Vision","AI4G: Machine Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}