{"type":"ScholarlyArticle","title":"Bridging the Objective Gap: A Unified Pre-Training Framework for Few-Shot Medical Image Segmentation","authors":[{"name":"Shoupeng Chen","slug":"shoupeng-chen","given":"Shoupeng","family":"Chen","affiliation":""},{"name":"Yiming Miao","slug":"yiming-miao","given":"Yiming","family":"Miao","affiliation":""},{"name":"Limei Peng","slug":"limei-peng","given":"Limei","family":"Peng","affiliation":""},{"name":"Pin-Han Ho","slug":"pin-han-ho","given":"Pin-Han","family":"Ho","affiliation":""}],"abstract":"Few-shot medical image segmentation relies on dense, boundary-sensitive prototype matching, yet common pre-training objectives mainly optimize global alignment or reconstruction, creating an objective gap that hurts boundary delineation and increases adaptation cost. This raises the question: how to pre-train representations intrinsically matchable for episodic FSS while requiring minimal adaptation-induced re-organization? We introduce a Drift-Gap diagnostic to quantify intrinsic dense-matching misalignment and adaptation-induced feature drift. Guided by this lens, we propose BOG-PRETRAIN, combining Reliability-Gated Alignment to mitigate noisy report supervision, Semantic-Guided MIM to emphasize boundary-informative regions, and Dual Consistency Regularization to stabilize episodic metric geometry. Across five benchmarks (1/4/16-shot), BOG-PRETRAIN improves mean Dice by +15.5/+15.9/+12.5 points over best priors and reduces mean HD95 by 0.9/4.6/10.1; it achieves the lowest Drift (0.052 vs. 0.155 baseline) and Gap_PT (0.256), with ablations confirming the components' complementarity.","doi":"10.24963/ijcai.2026/112","url":"https://ijcai.org/proceedings/2026/112","pdf":"https://ijcai.org/proceedings/2026/0112.pdf","markdown":"https://ijcai.org/proceedings/2026/112.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/112","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":112,"pages":{"first":998,"last":1006},"keywords":["Machine Learning: Few-shot learning","Computer Vision: Biomedical image analysis","Computer Vision: Segmentation, grouping and shape analysis"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}