{"ID":2895770,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.08711","arxiv_id":"2507.08711","title":"SGPMIL: Sparse Gaussian Process Multiple Instance Learning","abstract":"Multiple Instance Learning (MIL) offers a natural solution for settings where only coarse, bag-level labels are available, without having access to instance-level annotations. This is usually the case in digital pathology, which consists of gigapixel-sized images. While deterministic attention-based MIL approaches achieve strong bag-level performance, they often overlook the uncertainty inherent in instance relevance. In this paper, we address the lack of uncertainty quantification in instance-level attention scores by introducing SGPMIL, a new probabilistic attention-based MIL framework grounded in Sparse Gaussian Processes (SGP). By learning a posterior distribution over attention scores, SGPMIL enables principled uncertainty estimation, resulting in more reliable and calibrated instance relevance maps. Our approach not only preserves competitive bag-level performance but also significantly improves the quality and interpretability of instance-level predictions under uncertainty. SGPMIL extends prior work by introducing feature scaling in the SGP predictive mean function, leading to faster training, improved efficiency, and enhanced instance-level performance. Extensive experiments on multiple well-established digital pathology datasets highlight the effectiveness of our approach across both bag- and instance-level evaluations. Our code is available at https://github.com/mandlos/SGPMIL.","short_abstract":"Multiple Instance Learning (MIL) offers a natural solution for settings where only coarse, bag-level labels are available, without having access to instance-level annotations. This is usually the case in digital pathology, which consists of gigapixel-sized images. While deterministic attention-based MIL approaches achi...","url_abs":"https://arxiv.org/abs/2507.08711","url_pdf":"https://arxiv.org/pdf/2507.08711v2","authors":"[\"Andreas Lolos\",\"Stergios Christodoulidis\",\"Aris L. Moustakas\",\"Jose Dolz\",\"Maria Vakalopoulou\"]","published":"2025-07-11T16:10:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":612217,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2895770,"paper_url":"https://arxiv.org/abs/2507.08711","paper_title":"SGPMIL: Sparse Gaussian Process Multiple Instance Learning","repo_url":"https://github.com/mandlos/SGPMIL","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}