{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:38:59Z","timestamp":1773801539477,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>The deployment of large, black-box foundation models for medical image classification is often hindered by the high\ncost of acquiring large, task-specific labeled datasets for fine-tuning. While active learning (AL) presents a promising solution, many state-of-the-art AL methods are computationally\nexpensive or require full access to internal model parameters. We present VALIANT (Visual Adaptation and Learning\nIntegration for Active learNing Tasks), a new active learning framework designed to efficiently adapt black-box foundation models by overcoming these limitations. VALIANT\nintroduces a lightweight Visual Prompt Decoder (VIPD), trained via unsupervised Zero-Order Optimization (ZOO), to\ngenerate task-specific visual prompts without internal model access. Our core contribution is a perturbation-based ranking strategy that leverages this VIPD to formulate a computationally efficient, gradient-aware informativeness metric. This metric, which we term prompt instability, identifies the most impactful samples for the labeling budget. VALIANT\nfurther enhances this process by incorporating anatomical information from unsupervised segmentation maps to generate\nmore discriminative visual prompts. Extensive evaluations on multiple medical datasets demonstrate VALIANT\u2019s superior\nperformance and significant reduction in labeling costs compared to a range of existing active learning techniques, positioning it as a scalable and practical solution for medical\nimage analysis.<\/jats:p>","DOI":"10.1609\/aaai.v40i10.37734","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:40:26Z","timestamp":1773790826000},"page":"7901-7909","source":"Crossref","is-referenced-by-count":0,"title":["VALIANT: Prompt Instability for Active Learning in Black-Box Medical Imaging"],"prefix":"10.1609","volume":"40","author":[{"given":"Dwarikanath","family":"Mahapatra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Behzad","family":"Bozorgtabar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sudipta","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Imran","family":"Razzak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mauricio","family":"Reyes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37734\/41696","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37734\/41696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:40:26Z","timestamp":1773790826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37734"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i10.37734","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}