WildNet: Learning Domain Generalized Semantic Segmentation from the Wild

by   Suhyeon Lee, et al.

We present a new domain generalized semantic segmentation network named WildNet, which learns domain-generalized features by leveraging a variety of contents and styles from the wild. In domain generalization, the low generalization ability for unseen target domains is clearly due to overfitting to the source domain. To address this problem, previous works have focused on generalizing the domain by removing or diversifying the styles of the source domain. These alleviated overfitting to the source-style but overlooked overfitting to the source-content. In this paper, we propose to diversify both the content and style of the source domain with the help of the wild. Our main idea is for networks to naturally learn domain-generalized semantic information from the wild. To this end, we diversify styles by augmenting source features to resemble wild styles and enable networks to adapt to a variety of styles. Furthermore, we encourage networks to learn class-discriminant features by providing semantic variations borrowed from the wild to source contents in the feature space. Finally, we regularize networks to capture consistent semantic information even when both the content and style of the source domain are extended to the wild. Extensive experiments on five different datasets validate the effectiveness of our WildNet, and we significantly outperform state-of-the-art methods. The source code and model are available online: https://github.com/suhyeonlee/WildNet.


page 1

page 5

page 8

page 13

page 14

page 15

page 16

page 17


Semantic-Aware Domain Generalized Segmentation

Deep models trained on source domain lack generalization when evaluated ...

Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation

Domain-generalized urban-scene semantic segmentation (USSS) aims to lear...

DGSS : Domain Generalized Semantic Segmentation using Iterative Style Mining and Latent Representation Alignment

Semantic segmentation algorithms require access to well-annotated datase...

WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation

Domain generalization for semantic segmentation is highly demanded in re...

Adaptive Stylization Modulation for Domain Generalized Semantic Segmentation

Obtaining sufficient labelled data for model training is impractical for...

Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts

Improving model's generalizability against domain shifts is crucial, esp...

Style Interleaved Learning for Generalizable Person Re-identification

Domain generalization (DG) for person re-identification (ReID) is a chal...

Please sign up or login with your details

Forgot password? Click here to reset