用流匹配实现文本引导的精准图像分割，细节更清晰。
FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching
- 基于流匹配框架学习图像到掩码的时变向量场
- 在DIS-TE上达5.5%更高Fβ^ω，MAE降低43%
- 适合需要像素级控制的图像编辑与医学分割场景
准确的图像分割对图像编辑、自动驾驶和医学影像分析等应用至关重要。近年来，二分图像分割（DIS）已成为训练和评估高精度分割模型的标准任务。现有方法常难以保留细粒度细节或完整捕捉前景语义结构。为此，我们提出FlowDIS，一种基于流匹配框架的新型二分图像分割方法，通过学习时变向量场将图像分布传输至对应掩码分布，可选地受文本提示条件控制。此外，借助位置感知实例配对（PAIP）训练策略，FlowDIS实现强文本可控性，支持精确的像素级对象分割。大量实验表明，该方法在有无语言引导下均显著优于当前最优方法。相较于最佳先期方法，FlowDIS在DIS-TE测试集上实现5.5%更高的$F_β^ω$指标和43%更低的MAE($\mathcal{M}$)。代码已开源：https://github.com/Picsart-AI-Research/FlowDIS。
原文摘要 · Abstract (English)
Accurate image segmentation is essential for modern computer vision applications such as image editing, autonomous driving, and medical image analysis. In recent years, Dichotomous Image Segmentation (DIS) has become a standard task for training and evaluating highly accurate segmentation models. Existing DIS approaches often fail to preserve fine-grained details or fully capture the semantic structure of the foreground. To address these challenges, we present FlowDIS, a novel dichotomous image segmentation method built on the flow matching framework, which learns a time-dependent vector field to transport the image distribution to the corresponding mask distribution, optionally conditioned on a text prompt. Moreover, with our Position-Aware Instance Pairing (PAIP) training strategy, FlowDIS offers strong controllability through text prompts, enabling precise, pixel-level object segmentation. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches both with and without language guidance. Compared with the best prior DIS method, FlowDIS achieves a 5.5% higher $F_β^ω$ measure and 43% lower MAE ($\mathcal{M}$) on the DIS-TE test set. The code is available at: https://github.com/Picsart-AI-Research/FlowDIS
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。