ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation

• 类型：arxiv
• 标识：2609.03756
• 链接：https://arxiv.org/abs/2609.03756
• 主分类：rag
• 形态：method
• TLDR：We present ENEAS, a unified, text-promptable method for instance tracking and semantic discovery. Text-promptable segmentation models, including the latest foundation models such as SAM 3, still suffer from temporal hallucinations, spatial fragmentation, and semantic misclassification: they fail to report target absence when an object leaves the field of view, segment local textures instead of the complete object during extreme close-ups, and prioritize visual features over ontological reality, so that visually similar artifacts such as statues, paintings, or reflections are segmented as targe
• 待LLM分类：否
• 标题中文：ENEAS：嵌入引导的自适应分割神经集成
• TLDR中文：我们提出 ENEAS，一种用于实例追踪与语义发现的统一且文本可提示的方法。包括 SAM 3 在内的文本可提示分割模型仍存在时间幻觉、空间碎片化与语义误分类问题：目标离开视野时无法报告目标缺失；极端特写下只分割局部纹理而非完整目标；将视觉特征置于本体事实之上，从而把雕像、绘画或反射等视觉相似的物体误分割为目标。
• 来源文件：
• /inbox/tom/_candidates/2026-09-08-agent-rag-longcontext-candidates.json