{"slug": "u-cfr-uncertainty-guided-cascade-forward-refinement-for-interactive-segmentation", "title": "U-CFR: Uncertainty-Guided Cascade Forward Refinement for Interactive Segmentation", "summary": "Researchers propose Uncertainty-Guided Cascade Forward Refinement (U-CFR), a new inference-time framework for interactive image segmentation that enables models to autonomously self-correct after each user interaction. U-CFR introduces a boundary-aware uncertainty score to guide internal pseudo-clicks, reducing required clicks by over 10% on challenging datasets like Berkeley. The framework improves click efficiency, initial mask quality, and boundary accuracy.", "body_md": "arXiv:2607.20705v1 Announce Type: new\nAbstract: Interactive image segmentation is critical for efficient image annotation; however, existing methods often require many corrective clicks or rely on passive refinement schemes that converge slowly. We propose Uncertainty-Guided Cascade Forward Refinement (U-CFR), a novel inference-time framework that enables models to autonomously self-correct after each user interaction. U-CFR introduces a boundary-aware uncertainty score that fuses segmentation uncertainty, contour gradients, and explicit edge predictions to guide the placement of internal pseudo-clicks. These self-generated clicks target the most ambiguous boundary regions, providing strong corrective signals without additional manual input. To support this process, we design a dual-head network with a shared encoder-decoder backbone: a segmentation head ensures region consistency, while an edge head sharpens boundary alignment. In inference, U-CFR launches a cascade of refinement steps, where each stage leverages the uncertainty-driven pseudo-clicks to refine the mask progressively. Experiments on standard benchmark datasets demonstrate that the proposed U-CFR improves click efficiency, initial mask quality, and boundary accuracy. It reduces the required clicks by over 10% on challenging datasets like Berkeley and offers a more intelligent and efficient interactive annotation.", "url": "https://wpnews.pro/news/u-cfr-uncertainty-guided-cascade-forward-refinement-for-interactive-segmentation", "canonical_source": "https://arxiv.org/abs/2607.20705", "published_at": "2026-07-24 04:00:00+00:00", "updated_at": "2026-07-24 04:28:14.649535+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "artificial-intelligence"], "entities": ["U-CFR", "Berkeley"], "alternates": {"html": "https://wpnews.pro/news/u-cfr-uncertainty-guided-cascade-forward-refinement-for-interactive-segmentation", "markdown": "https://wpnews.pro/news/u-cfr-uncertainty-guided-cascade-forward-refinement-for-interactive-segmentation.md", "text": "https://wpnews.pro/news/u-cfr-uncertainty-guided-cascade-forward-refinement-for-interactive-segmentation.txt", "jsonld": "https://wpnews.pro/news/u-cfr-uncertainty-guided-cascade-forward-refinement-for-interactive-segmentation.jsonld"}}