{"slug": "dual-adaptive-sam3-hierarchical-routing-over-low-rank-expert-layers-for-medical", "title": "Dual-Adaptive SAM3: Hierarchical Routing over Low-Rank Expert Layers for Parameter-Efficient Medical Image Segmentation", "summary": "Researchers propose Dual-Adaptive SAM3 (DA-SAM3), a framework for parameter-efficient medical image segmentation that uses a Dynamic Expert Router and Decomposed Parameterized Experts to reduce MoE overhead by over 80% while achieving state-of-the-art accuracy. The method matches or exceeds fully fine-tuned SAM3 and standard MoE baselines, with a 5% gain over current methods on public benchmarks.", "body_md": "arXiv:2607.02571v1 Announce Type: new\nAbstract: The Segment Anything Model with Concepts (SAM3) heralds a new paradigm for open-vocabulary segmentation through natural language interaction, offering significant potential for medical image analysis. However, effectively adapting such a powerful vision-language model to the diverse and nuanced domain of medical imaging remains a key challenge. Naive fine-tuning is parameter-inefficient, while standard Mixture-of-Experts (MoE) methods introduce prohibitive computational overhead, limiting their clinical applicability. To address this, we propose Dual-Adaptive SAM3 (DA-SAM3), a novel framework that achieves both high segmentation accuracy and extreme parameter efficiency via a dual-adaptive specialization mechanism. Our first adaptation is task-aware: a Dynamic Expert Router (DER) that sparsely activates the most relevant experts by jointly reasoning about the visual input and the textual concept prompt, mimicking a clinical consultation process. Our second adaptation is parameter-aware: a Decomposed Parameterized Experts (DPE) design that represents each expert as a shared frozen base (inherited from the pretrained SAM3) and a lightweight trainable low-rank delta, reducing MoE parameter overhead by over 80\\%. Extensive experiments on multiple public medical segmentation benchmarks demonstrate that Dual-Adaptive SAM3 not only matches or exceeds the accuracy of fully fine-tuned SAM3 and standard MoE baselines, but also achieves a notable 5\\% gain over current state-of-the-art methods, with interpretable results validating its effectiveness. The code is available at: https://github.com/Reconsider80/DA-SAM3.", "url": "https://wpnews.pro/news/dual-adaptive-sam3-hierarchical-routing-over-low-rank-expert-layers-for-medical", "canonical_source": "https://arxiv.org/abs/2607.02571", "published_at": "2026-07-07 04:00:00+00:00", "updated_at": "2026-07-07 04:08:00.961467+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "large-language-models", "ai-research"], "entities": ["SAM3", "Dual-Adaptive SAM3", "DA-SAM3", "Dynamic Expert Router", "Decomposed Parameterized Experts"], "alternates": {"html": "https://wpnews.pro/news/dual-adaptive-sam3-hierarchical-routing-over-low-rank-expert-layers-for-medical", "markdown": "https://wpnews.pro/news/dual-adaptive-sam3-hierarchical-routing-over-low-rank-expert-layers-for-medical.md", "text": "https://wpnews.pro/news/dual-adaptive-sam3-hierarchical-routing-over-low-rank-expert-layers-for-medical.txt", "jsonld": "https://wpnews.pro/news/dual-adaptive-sam3-hierarchical-routing-over-low-rank-expert-layers-for-medical.jsonld"}}