PANC: Prior-Aware Normalized Cut via Anchor-Augmented Token Graphs

arXiv:2602.06912v2 Announce Type: replace Abstract: 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.

Related

• PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation
• OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation
• OpenTrack3D: Towards Accurate and Generalizable Open-Vocabulary 3D Instance Segmentation
• Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation

Source: arXiv cs.CV | 2026-04-10