Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2602.06912 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913017744064512 |
|---|---|
| author | Gutiérrez, Juan Gutiérrez-García, Victor Blanco-Murillo, José Luis |
| author_facet | Gutiérrez, Juan Gutiérrez-García, Victor Blanco-Murillo, José Luis |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06912 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PANC: Prior-Aware Normalized Cut via Anchor-Augmented Token Graphs Gutiérrez, Juan Gutiérrez-García, Victor Blanco-Murillo, José Luis Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | PANC: Prior-Aware Normalized Cut via Anchor-Augmented Token Graphs |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2602.06912 |