PANC: Prior-Aware Normalized Cut for Training-Free In-Context Segmentation
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.