用先验信息增强视觉片段分割，提升无监督方法的稳定性与准确性
PANC: Prior-Aware Normalized Cut via Anchor-Augmented Token Graphs
- 通过锚点连接先验标记，构建带先验引导的图谱割算法
- 在低语义图像上实现8.7% mIoU提升，显著优于现有方法
- 无需训练，可交互控制分割结果，适合无标注场景应用
自监督视觉变换器（ViT）块的无监督分割具有潜力，但鲁棒性不足：多对象场景会混淆显著性线索，低语义图像削弱块相关性，导致掩码不一致。为此，我们提出先验感知归一化割（PANC），一种无需训练的数据高效方法，能生成一致且可用户调控的分割结果。PANC通过将已知先验标记块连接至前景/背景锚点，构建锚点增强的广义特征值问题，引导低频划分向目标类别偏移，同时保持全局谱结构。结合先验感知特征向量方向与阈值处理，方法生成稳定掩码。谱诊断表明，注入先验可扩大特征值间隙并稳定划分，符合理论假设。PANC超越强无监督和弱监督基线，在DUTS-TE上提升2.3% mIoU，DUT-OMRON上提升2.8%，在低语义的CrackForest数据集上提升8.7%。
原文摘要 · Abstract (English)
Unsupervised segmentation from self-supervised ViT patches holds promise but lacks robustness: multi-object scenes confound saliency cues, and low-semantic images weaken patch relevance, both leading to erratic masks. To address this, we present Prior-Aware Normalized Cut (PANC), a training-free method that data-efficiently produces consistent, user-steerable segmentations. PANC extends the Normalized Cut algorithm by connecting labeled prior tokens to foreground/background anchors, forming an anchor-augmented generalized eigenproblem that steers low-frequency partitions toward the target class while preserving global spectral structure. With prior-aware eigenvector orientation and thresholding, our approach yields stable masks. Spectral diagnostics confirm that injected priors widen eigengaps and stabilize partitions, consistent with our analytical hypotheses. PANC outperforms strong unsupervised and weakly supervised baselines, achieving mIoU improvements of +2.3% on DUTS-TE, +2.8% on DUT-OMRON, and +8.7% on low-semantic CrackForest datasets.
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。