{"type":"ScholarlyArticle","title":"ReDi-FM: Frozen Foundation Model for Continual Test-Time Adaptation in Medical Image Segmentation","authors":[{"name":"Jianhang Ji","slug":"jianhang-ji","given":"Jianhang","family":"Ji","affiliation":""},{"name":"Zhiming Cheng","slug":"zhiming-cheng","given":"Zhiming","family":"Cheng","affiliation":""},{"name":"Jianxiang Zhao","slug":"jianxiang-zhao","given":"Jianxiang","family":"Zhao","affiliation":""},{"name":"Tingyu Wang","slug":"tingyu-wang","given":"Tingyu","family":"Wang","affiliation":""},{"name":"Bingtao Ma","slug":"bingtao-ma","given":"Bingtao","family":"Ma","affiliation":""},{"name":"Yuhan Gao","slug":"yuhan-gao","given":"Yuhan","family":"Gao","affiliation":""},{"name":"Zuobin Ying","slug":"zuobin-ying","given":"Zuobin","family":"Ying","affiliation":""},{"name":"Shuai Wang","slug":"shuai-wang","given":"Shuai","family":"Wang","affiliation":""}],"abstract":"Continual test-time adaptation (CTTA) adapts a pre-trained medical segmentation model online to an unlabeled target stream whose distribution changes over time. However, most existing CTTA methods rely on pseudo-labeling and self-supervised objectives, which inevitably yield noisy supervision under domain shifts. To mitigate this limitation, we introduce off-the-shelf Vision Foundation Models (VFMs) as external knowledge sources. Zero-shot VFMs are insufficient for medical segmentation because they lack medical semantics, yet they contain rich and heterogeneous generic knowledge. To exploit such external knowledge, we propose Reciprocal Distillation with a Frozen Foundation Model (ReDi-FM), a novel framework with two core components: using structure-aware prompts from the source model to guide the frozen VFM to generate target-adapted supervision, and distilling the resulting knowledge back into the adapting model. For robust distillation, we introduce two complementary objectives: uncertainty-driven hard distillation for precise guidance in ambiguous regions, and hard class-balanced soft distillation for richer supervision of under-represented and challenging structures. A consensus-aware gate further stabilizes adaptation when the two teachers disagree. Extensive experiments on multi-domain medical segmentation benchmarks demonstrate that ReDi-FM outperforms state-of-the-art CTTA methods. Code is available at https://github.com/M4cheal/ReDi-FM.","doi":"10.24963/ijcai.2026/140","url":"https://ijcai.org/proceedings/2026/140","pdf":"https://ijcai.org/proceedings/2026/0140.pdf","markdown":"https://ijcai.org/proceedings/2026/140.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/140","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":"Computer Vision","track":"Main Track","number":140,"pages":{"first":1252,"last":1260},"keywords":["Computer Vision: Transfer, low-shot, semi- and un- supervised learning","Computer Vision: Biomedical image analysis","Computer Vision: Segmentation, grouping and shape analysis"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}