WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation

Abstract

Domain generalization for semantic segmentation is highly demanded in real applications, where a trained model is expected to work well in previously unseen domains. One challenge lies in the lack of data which could cover the diverse distributions of the possible unseen domains for training. In this paper, we propose a WEb-image assisted Domain GEneralization (WEDGE) scheme, which is the first to exploit the diversity of web-crawled images for generalizable semantic segmentation. To explore and exploit the real-world data distributions, we collect web-crawled images which present large diversity in terms of weather conditions, sites, lighting, camera styles, etc. We also present a method which injects styles of the web-crawled images into training images on-the-fly during training, which enables the network to experience images of diverse styles with reliable labels for effective training. Moreover, we use the web-crawled images with their predicted pseudo labels for training to further enhance the capability of the network. Extensive experiments demonstrate that our method clearly outperforms existing domain generalization techniques.

References in corpus (7)

• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Generalization via Invariant Feature Representation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
• Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
• Automated Synthetic-to-Real Generalization