让超像素既准确又规则，还能交互聚焦特定物体。
Superpixel Anything: A general object-based framework for accurate yet regular superpixel segmentation
- 用预训练模型提取语义无关特征生成超像素。
- 在多个数据集上精度超越现有方法，且保持形状规则。
- 适合需要可解释性分割的视觉任务，如医学图像分析。
超像素广泛用于简化图像表示并降低计算复杂度。传统方法依赖低级特征，深度学习方法虽利用高级特征但常牺牲超像素的规则性以捕捉复杂对象，导致分割准确却难以解释。本文提出SPAM（SuperPixel Anything Model），一种通用框架，可在保证准确性的前提下生成规则的超像素。通过训练模型提取图像特征用于超像素生成，并在推理时利用大规模预训练模型进行语义无关分割，确保超像素与物体掩码对齐。SPAM可处理任意高层分割先验，解决不确定区域问题，支持交互式关注特定对象。大量实验表明，其在分割任务上定性和定量均优于当前最优方法，是多种应用中的强大可靠工具。代码与预训练模型已开源：https://github.com/waldo-j/spam。
原文摘要 · Abstract (English)
Superpixels are widely used in computer vision to simplify image representation and reduce computational complexity. While traditional methods rely on low-level features, deep learning-based approaches leverage high-level features but also tend to sacrifice regularity of superpixels to capture complex objects, leading to accurate but less interpretable segmentations. In this work, we introduce SPAM (SuperPixel Anything Model), a versatile framework for segmenting images into accurate yet regular superpixels. We train a model to extract image features for superpixel generation, and at inference, we leverage a large-scale pretrained model for semantic-agnostic segmentation to ensure that superpixels align with object masks. SPAM can handle any prior high-level segmentation, resolving uncertainty regions, and is able to interactively focus on specific objects. Comprehensive experiments demonstrate that SPAM qualitatively and quantitatively outperforms state-of-the-art methods on segmentation tasks, making it a valuable and robust tool for various applications. Code and pre-trained models are available here: https://github.com/waldo-j/spam.
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。