English

Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization

Computer Vision and Pattern Recognition 2021-04-14 v1 Artificial Intelligence Machine Learning

Abstract

Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available unlabeled data to complement small labeled data sets. In this paper, we propose a novel framework for discriminative pixel-level tasks using a generative model of both images and labels. Concretely, we learn a generative adversarial network that captures the joint image-label distribution and is trained efficiently using a large set of unlabeled images supplemented with only few labeled ones. We build our architecture on top of StyleGAN2, augmented with a label synthesis branch. Image labeling at test time is achieved by first embedding the target image into the joint latent space via an encoder network and test-time optimization, and then generating the label from the inferred embedding. We evaluate our approach in two important domains: medical image segmentation and part-based face segmentation. We demonstrate strong in-domain performance compared to several baselines, and are the first to showcase extreme out-of-domain generalization, such as transferring from CT to MRI in medical imaging, and photographs of real faces to paintings, sculptures, and even cartoons and animal faces. Project Page: \url{https://nv-tlabs.github.io/semanticGAN/}

Keywords

Cite

@article{arxiv.2104.05833,
  title  = {Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization},
  author = {Daiqing Li and Junlin Yang and Karsten Kreis and Antonio Torralba and Sanja Fidler},
  journal= {arXiv preprint arXiv:2104.05833},
  year   = {2021}
}

Comments

CVPR2021

R2 v1 2026-06-24T01:06:04.816Z