用置信度引导的抠图方法提升图像分割边界精度
BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation
- 基于置信度对分割结果进行抠图式精细化
- 在DIS5K数据集上优于当前最优方法
- 适合需要精准边界的图像分割任务
当前二值图像分割（DIS）方法将图像抠图与对象分割视为本质不同的任务。随着分割性能提升愈发困难，结合抠图与灰度分割技术为架构创新带来新方向。受此启发，我们提出一种新型DIS架构——置信度引导抠图（CGM），并构建首个CGM模型：背景消除网络（BEN）。BEN由两部分组成：BEN Base负责初始分割，BEN Refiner实现基于置信度的精细化优化。该方法在DIS5K验证集上显著超越现有最先进方法，证明了基于抠图的细化能大幅提升分割质量。本工作提出一种融合抠图与分割的新范式，显著改善计算机视觉中细粒度物体边界的预测能力。
原文摘要 · Abstract (English)
Current approaches to dichotomous image segmentation (DIS) treat image matting and object segmentation as fundamentally different tasks. As improvements in image segmentation become increasingly challenging to achieve, combining image matting and grayscale segmentation techniques offers promising new directions for architectural innovation. Inspired by the possibility of aligning these two model tasks, we propose a new architectural approach for DIS called Confidence-Guided Matting (CGM). We created the first CGM model called Background Erase Network (BEN). BEN consists of two components: BEN Base for initial segmentation and BEN Refiner for confidence-based refinement. Our approach achieves substantial improvements over current state-of-the-art methods on the DIS5K validation dataset, demonstrating that matting-based refinement can significantly enhance segmentation quality. This work introduces a new paradigm for integrating matting and segmentation techniques, improving fine-grained object boundary prediction in computer vision.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。