Intra-Source Style Augmentation for Improved Domain Generalization

by   Yumeng Li, et al.

The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning models. Therefore, we propose an intra-source style augmentation (ISSA) method to improve domain generalization in semantic segmentation. Our method is based on a novel masked noise encoder for StyleGAN2 inversion. The model learns to faithfully reconstruct the image preserving its semantic layout through noise prediction. Random masking of the estimated noise enables the style mixing capability of our model, i.e. it allows to alter the global appearance without affecting the semantic layout of an image. Using the proposed masked noise encoder to randomize style and content combinations in the training set, ISSA effectively increases the diversity of training data and reduces spurious correlation. As a result, we achieve up to 12.4% mIoU improvements on driving-scene semantic segmentation under different types of data shifts, i.e., changing geographic locations, adverse weather conditions, and day to night. ISSA is model-agnostic and straightforwardly applicable with CNNs and Transformers. It is also complementary to other domain generalization techniques, e.g., it improves the recent state-of-the-art solution RobustNet by 3% mIoU in Cityscapes to Dark Zürich.


page 3

page 4

page 5

page 6

page 13

page 15

page 16

page 17


Intra- Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization

The generalization with respect to domain shifts, as they frequently app...

Domain generalization of 3D semantic segmentation in autonomous driving

3D autonomous driving semantic segmentation using deep learning has beco...

Benchmarking the Robustness of Semantic Segmentation Models

When designing a semantic segmentation module for a practical applicatio...

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

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

Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers

For safety-critical applications such as autonomous driving, CNNs have t...

A Style and Semantic Memory Mechanism for Domain Generalization

Mainstream state-of-the-art domain generalization algorithms tend to pri...

Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers

Imaging through diffusive media is a challenging problem, where the exis...

Please sign up or login with your details

Forgot password? Click here to reset