{"type":"post","id":"bald-sam-adds-bayesian-active-learning-on-top-b32aaf","slug":"bald-sam-adds-bayesian-active-learning-on-top-b32aaf","title":"BALD-SAM adds Bayesian active learning on top of frozen SAM to pick the most informative next prompt.","description":"BALD-SAM is a research method for choosing the next spatial prompt in interactive image segmentation by estimating where another human input would be most informative.","retrieval_nugget":"BALD-SAM is a research method for choosing the next spatial prompt in interactive image segmentation by estimating where another human input would be most informative. Its authors report first- or second-place results on 14 of 16 datasets, pointing to a way to focus annotation effort on ambiguous regions rather than visual inspection alone.","published_at":"2026-11-10","updated_at":"2026-11-10","record_date":"2026-11-10","date_kind":"published_at","topics":["models","multimodal"],"entities":["BALD-SAM","Segment Anything Model","Prithwijit Chowdhury","Mohit Prabhushankar","Ghassan AlRegib"],"related_patterns":[],"novelty_label":"new_fact","what_changed":"BALD-SAM applies Bayesian active learning to SAM prompts, selecting informative regions while freezing the main model and reporting strong results across 16 datasets.","prior_refs":[],"source_url":"https://arxiv.org/abs/2603.10828","source_urls":["https://arxiv.org/abs/2603.10828"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:bald-sam-adds-bayesian-active-learning-on-top-b32aaf","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/bald-sam-adds-bayesian-active-learning-on-top-b32aaf/","markdown":"https://newruntime.com/posts/bald-sam-adds-bayesian-active-learning-on-top-b32aaf.md","json":"https://newruntime.com/posts/bald-sam-adds-bayesian-active-learning-on-top-b32aaf.json"},"markdown_url":"https://newruntime.com/posts/bald-sam-adds-bayesian-active-learning-on-top-b32aaf.md","next_reads":[{"type":"topic","path":"/topics/models/","url":"https://newruntime.com/topics/models/","title":"Models","reason":"Explore the models topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/models.md","json_url":"https://newruntime.com/topics/models.json"},{"type":"topic","path":"/topics/multimodal/","url":"https://newruntime.com/topics/multimodal/","title":"Multimodal","reason":"Explore the multimodal topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/multimodal.md","json_url":"https://newruntime.com/topics/multimodal.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}