{"ID":2878874,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17283","arxiv_id":"2508.17283","title":"Quickly Tuning Foundation Models for Image Segmentation","abstract":"Foundation models like SAM (Segment Anything Model) exhibit strong zero-shot image segmentation performance, but often fall short on domain-specific tasks. Fine-tuning these models typically requires significant manual effort and domain expertise. In this work, we introduce QTT-SEG, a meta-learning-driven approach for automating and accelerating the fine-tuning of SAM for image segmentation. Built on the Quick-Tune hyperparameter optimization framework, QTT-SEG predicts high-performing configurations using meta-learned cost and performance models, efficiently navigating a search space of over 200 million possibilities. We evaluate QTT-SEG on eight binary and five multiclass segmentation datasets under tight time constraints. Our results show that QTT-SEG consistently improves upon SAM's zero-shot performance and surpasses AutoGluon Multimodal, a strong AutoML baseline, on most binary tasks within three minutes. On multiclass datasets, QTT-SEG delivers consistent gains as well. These findings highlight the promise of meta-learning in automating model adaptation for specialized segmentation tasks. Code available at: https://github.com/ds-brx/QTT-SEG/","short_abstract":"Foundation models like SAM (Segment Anything Model) exhibit strong zero-shot image segmentation performance, but often fall short on domain-specific tasks. Fine-tuning these models typically requires significant manual effort and domain expertise. In this work, we introduce QTT-SEG, a meta-learning-driven approach for...","url_abs":"https://arxiv.org/abs/2508.17283","url_pdf":"https://arxiv.org/pdf/2508.17283v1","authors":"[\"Breenda Das\",\"Lennart Purucker\",\"Timur Carstensen\",\"Frank Hutter\"]","published":"2025-08-24T10:06:02Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":610518,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2878874,"paper_url":"https://arxiv.org/abs/2508.17283","paper_title":"Quickly Tuning Foundation Models for Image Segmentation","repo_url":"https://github.com/ds-brx/QTT-SEG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}