用动态引导框架提升无监督分割精度，兼顾全局语义与边界细节。
DynaGuide: A Generalizable Dynamic Guidance Framework for Unsupervised Semantic Segmentation
- 融合零样本模型全局伪标签与轻量CNN局部边界优化
- 在BSD500、PASCAL VOC2012、COCO上分别提升mIoU 17.5%、3.1%、11.66%
- 无需目标域真值标签，可灵活接入多种引导源，适合实际部署
无监督图像分割是计算机视觉中的关键任务，能在无人工标注情况下实现密集场景理解，尤其适用于标注数据稀缺的领域。然而，现有方法常难以同时兼顾全局语义结构与细粒度边界精度。本文提出DynaGuide，一种自适应分割框架，通过创新的双引导策略与动态损失优化解决上述挑战。基于先前工作DynaSeg，DynaGuide结合来自DiffSeg或SegFormer等零样本模型的全局伪标签，以及从零开始训练的轻量级CNN进行局部边界精炼。这种协同机制可修正粗略或噪声较大的全局预测，生成高精度分割结果。DynaGuide的核心是多组件动态损失，平衡特征相似性、Huber平滑的空间连续性（含对角关系）及与全局伪标签的语义一致性。不同于以往方法，DynaGuide在目标域完全无需真值标签进行训练，并支持多种引导源的即插即用集成。在BSD500、PASCAL VOC2012和COCO上的大量实验表明，DynaGuide达到当前最优性能，分别提升mIoU 17.5%、3.1%和11.66%。其模块化设计、强泛化能力与极低计算开销，使其成为真实场景中无监督分割的可扩展实用方案。代码已开源：https://github.com/RyersonMultimediaLab/DynaGuide
原文摘要 · Abstract (English)
Unsupervised image segmentation is a critical task in computer vision. It enables dense scene understanding without human annotations, which is especially valuable in domains where labelled data is scarce. However, existing methods often struggle to reconcile global semantic structure with fine-grained boundary accuracy. This paper introduces DynaGuide, an adaptive segmentation framework that addresses these challenges through a novel dual-guidance strategy and dynamic loss optimization. Building on our previous work, DynaSeg, DynaGuide combines global pseudo-labels from zero-shot models such as DiffSeg or SegFormer with local boundary refinement using a lightweight CNN trained from scratch. This synergy allows the model to correct coarse or noisy global predictions and produce high-precision segmentations. At the heart of DynaGuide is a multi-component loss that dynamically balances feature similarity, Huber-smoothed spatial continuity, including diagonal relationships, and semantic alignment with the global pseudo-labels. Unlike prior approaches, DynaGuide trains entirely without ground-truth labels in the target domain and supports plug-and-play integration of diverse guidance sources. Extensive experiments on BSD500, PASCAL VOC2012, and COCO demonstrate that DynaGuide achieves state-of-the-art performance, improving mIoU by 17.5% on BSD500, 3.1% on PASCAL VOC2012, and 11.66% on COCO. With its modular design, strong generalization, and minimal computational footprint, DynaGuide offers a scalable and practical solution for unsupervised segmentation in real-world settings. Code available at: https://github.com/RyersonMultimediaLab/DynaGuide
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。