Poster

GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models

Chen Liang · Wenguan Wang · Jiaxu Miao · Yi Yang

Hall J #631

Keywords: [ Anomaly Segmentation ] [ generative classifier ] [ semantic segmentation ]

[ Abstract ]
[ Slides [ OpenReview
Wed 30 Nov 2 p.m. PST — 4 p.m. PST
 
Spotlight presentation: Lightning Talks 1A-4
Tue 6 Dec 10:30 a.m. PST — 10:45 a.m. PST

Abstract:

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.

Chat is not available.