论文标题
GMMSEG：基于高斯混合物的生成语义分割模型
GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models
论文作者
论文摘要
从本质上讲，普遍的语义分割解决方案是P的密集判别分类器（类|像素特征）。尽管很简单，但这种事实上的范式却忽略了基本数据分布p（像素功能|类），并努力识别分布数据外数据。除此之外，我们提出了GMMSEG，这是一个新的分割模型系列，它们依赖于关节分布P的密集生成分类器（Pixel功能，类）。对于每个类别，GMMSEG通过预期最大化（EM）构建高斯混合模型（GMM），以捕获类条件密度。同时，深度密集表示以歧视方式进行了端到端训练，即最大化P（类|像素特征）。这赋予了Gmmseg的生成和判别模型的优势。 GMMSEG凭借各种分割体系结构和骨干，在三个封闭式数据集上的歧视性对应物优于歧视性。更令人印象深刻的是，没有任何修改，GMMSEG甚至在开放世界数据集上表现良好。我们相信这项工作为相关领域带来了基本的见解。
Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier of p(class|pixel feature). Though straightforward, this de facto paradigm neglects the underlying data distribution p(pixel feature|class), and struggles to identify out-of-distribution data. Going beyond this, we propose GMMSeg, a new family of segmentation models that rely on a dense generative classifier for the joint distribution p(pixel feature,class). For each class, GMMSeg builds Gaussian Mixture Models (GMMs) via Expectation-Maximization (EM), so as to capture class-conditional densities. Meanwhile, the deep dense representation is end-to-end trained in a discriminative manner, i.e., maximizing p(class|pixel feature). This endows GMMSeg with the strengths of both generative and discriminative models. With a variety of segmentation architectures and backbones, GMMSeg outperforms the discriminative counterparts on three closed-set datasets. More impressively, without any modification, GMMSeg even performs well on open-world datasets. We believe this work brings fundamental insights into the related fields.
