{"ID":2839675,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.15771","arxiv_id":"2511.15771","title":"UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation","abstract":"The Segment Anything Model 2 (SAM2) demonstrates remarkable universal segmentation capabilities on natural images. However, its performance on ultrasound images is significantly degraded due to domain disparities. This limitation raises two critical challenges: how to efficiently adapt SAM2 to ultrasound imaging while maintaining parameter efficiency, and how to deploy the adapted model effectively in resource-constrained clinical environments. To address these issues, we propose UniUltra for universal ultrasound segmentation. Specifically, we first introduce a novel context-edge hybrid adapter (CH-Adapter) that enhances fine-grained perception across diverse ultrasound imaging modalities while achieving parameter-efficient fine-tuning. To further improve clinical applicability, we develop a deep-supervised knowledge distillation (DSKD) technique that transfers knowledge from the large image encoder of the fine-tuned SAM2 to a super lightweight encoder, substantially reducing computational requirements without compromising performance. Extensive experiments demonstrate that UniUltra outperforms state-of-the-arts with superior generalization capabilities. Notably, our framework achieves competitive performance using only 8.91% of SAM2's parameters during fine-tuning, and the final compressed model reduces the parameter count by 94.08% compared to the original SAM2, making it highly suitable for practical clinical deployment. The source code is available at https://github.com/xq141839/UniUltra.","short_abstract":"The Segment Anything Model 2 (SAM2) demonstrates remarkable universal segmentation capabilities on natural images. However, its performance on ultrasound images is significantly degraded due to domain disparities. This limitation raises two critical challenges: how to efficiently adapt SAM2 to ultrasound imaging while...","url_abs":"https://arxiv.org/abs/2511.15771","url_pdf":"https://arxiv.org/pdf/2511.15771v1","authors":"[\"Yue Li\",\"Qing Xu\",\"Yixuan Zhang\",\"Xiangjian He\",\"Qian Zhang\",\"Yuan Yao\",\"Fiseha B. Tesem\",\"Xin Chen\",\"Ruili Wang\",\"Zhen Chen\",\"Chang Wen Chen\"]","published":"2025-11-19T17:42:49Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":606894,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839675,"paper_url":"https://arxiv.org/abs/2511.15771","paper_title":"UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation","repo_url":"https://github.com/xq141839/UniUltra","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}