发表机构
KAIST（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出用二元偏好替代密集掩码的适配框架，利用提示分歧作为内置偏好来源，通过区域局部化偏好优化与一致性正则化，在无需像素级标注下提升开放词汇语义分割在专业领域的性能。
AI 中文摘要
开放词汇语义分割（OVSS）能够对任意文本指定的词汇进行像素级预测，并在常见基准上展现出强大的泛化能力。然而，在医学影像、遥感探测和工业检测等专业领域，OVSS的性能往往会下降，因为在这些领域中，获取用于适配的密集像素级掩码成本高昂，且需要领域专业知识。我们提出了一种偏好引导的适配框架，用二元偏好替代密集掩码监督。我们观察到，对于同一图像，不同的提示模板会产生系统性的不同分割结果，我们将这一现象称为“提示分歧”，并将其重新用作内置的偏好监督来源。在此基础上，我们从高交叉模板不确定性区域挖掘局部化偏好查询，并通过区域局部化偏好优化（RLPO）以及一致性正则化来适配OVSS模型，该正则化可稳定查询区域之外的更新。在MESS基准上的大量实验中，所提方法在多种OVSS骨干网络上取得了一致的性能提升，且无需任何像素级标注，并在噪声偏好下依然有效。我们的代码可在以下网址获取：此https URL。
英文摘要
Open-vocabulary semantic segmentation (OVSS) enables pixel-level prediction over arbitrary text-specified vocabularies and has shown strong generalization on common benchmarks. However, OVSS performance often degrades in specialized domains such as medical imaging, remote sensing, and industrial inspection, where dense pixel-level masks for adaptation are costly to obtain and require domain-specific expertise. We propose a preference-guided adaptation framework that replaces dense mask supervision with binary preferences. We observe that different prompt templates produce systematically different segmentations for the same image, a phenomenon we call prompt disagreement, and we repurpose it as a built-in source of preference supervision. Building on this, we mine localized preference queries from regions of high cross-template uncertainty, and adapt the OVSS model with Region-Localized Preference Optimization (RLPO) together with consistency regularization that stabilizes updates outside the queried region. Across extensive experiments on the MESS benchmark, the proposed method achieves consistent gains across diverse OVSS backbones without any pixel-level annotation, and remains effective under noisy preferences. Our code is available at https://github.com/blue-531/pref-ovss.
CommentsAccepted to NeurIPS 2026
