{"type":"ScholarlyArticle","title":"Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression","authors":[{"name":"Chunlai Dong","slug":"chunlai-dong","given":"Chunlai","family":"Dong","affiliation":""},{"name":"Haochao Ying","slug":"haochao-ying","given":"Haochao","family":"Ying","affiliation":""},{"name":"Qibo Qiu","slug":"qibo-qiu","given":"Qibo","family":"Qiu","affiliation":""},{"name":"Jinhong Wang","slug":"jinhong-wang","given":"Jinhong","family":"Wang","affiliation":""},{"name":"Danny Chen","slug":"danny-chen","given":"Danny","family":"Chen","affiliation":""},{"name":"Jian Wu","slug":"jian-wu","given":"Jian","family":"Wu","affiliation":""}],"abstract":"Ordinal regression bridges regression and classification by assigning objects to ordered classes. While human experts rely on discriminative patch-level features for decisions, current approaches are limited by the availability of only image-level ordinal labels, overlooking fine-grained patch-level characteristics. In this paper, we propose a Dual-level Fuzzy Learning with Patch Guidance framework, named DFPG that learns precise feature-based grading boundaries from ambiguous ordinal labels, with patch-level supervision. Specifically, we propose patch-labeling and filtering strategies to enable the model to focus on patch-level features exclusively with only image-level ordinal labels available. We further design a dual-level fuzzy learning module, which leverages fuzzy logic to quantitatively capture and handle label ambiguity from both patch-wise and channel-wise perspectives. Extensive experiments on various image ordinal regression datasets demonstrate the superiority of our proposed method, further confirming its ability in distinguishing samples from difficult-to-classify categories. The code is available at https://github.com/ZJUMAI/DFPG-ord.","doi":"10.24963/ijcai.2025/103","url":"https://ijcai.org/proceedings/2025/103","pdf":"https://ijcai.org/proceedings/2025/0103.pdf","markdown":"https://ijcai.org/proceedings/2025/103.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/103","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":103,"pages":{"first":918,"last":926},"keywords":["Multidisciplinary Topics and Applications: MTA: Health and medicine","Computer Vision: CV: Recognition (object detection, categorization)"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}