arXiv cs.AI· Juan Guti\'errez, Victor Guti\'errez-Garc\'ia, Jos\'e Luis Blanco-Murillo·· 2 小时前AI 评分30
PANC:面向免训练上下文分割的先验感知 Normalized Cut 方法
PANC: Prior-Aware Normalized Cut for Training-Free In-Context Segmentation
AI 导读
PANC 是一种免训练的先验感知谱分割方法,通过前景/背景锚点节点将外部标注 token 注入冻结 ViT 亲和图, softly 偏置 Normalized Cut 特征空间。相比 TokenCut 等类无关方法,它在多目标场景和低语义纹理主导域中更稳定,并在异质显著性数据集与同质低语义域上优于无先验基线,模糊或弱显著性场景收益最大。论文已被 WACV 2027 接收。
正文 · 原文
Abstract:We study training-free in-context segmentation with externally annotated context priors: given a target image and a small set of foreground/background tokens extracted from annotated context images, the goal is to segment the corresponding target concept without training, fine-tuning, or target-image clicks. Existing ViT-token spectral methods such as TokenCut are class-agnostic and can select the wrong object in multi-object scenes, or become unstable in low-semantic texture-dominated domains. We propose PANC, a prior-aware spectral segmentation pipeline that injects external labeled tokens into a frozen ViT affinity graph through two foreground/background anchor nodes. The anchors do not clamp target-image tokens; instead, they softly bias the Normalized Cut eigenspace while preserving the target-image affinity structure. PANC further uses prior-aware sign stabilization and prior-driven thresholding to obtain deterministic masks. Across heterogeneous saliency datasets and homogeneous low-semantic domains, PANC improves over architecture-matched no-prior token-graph baselines, with the largest gains in settings where class-agnostic saliency is ambiguous or weak.
| Comments: | Accepted to WACV 2027 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.06912 [cs.CV] |
| (or arXiv:2602.06912v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2602.06912 arXiv-issued DOI via DataCite |
Submission history
From: Juan Gutiérrez [view email]
[v1]
Fri, 6 Feb 2026 18:07:20 UTC (12,902 KB)
[v2]
Wed, 8 Apr 2026 22:13:53 UTC (32,432 KB)
[v3]
Wed, 18 Nov 2026 17:20:41 UTC (26,495 KB)
来源:arXiv cs.AI · arxiv.org