Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data

09/02/2019
by   Xiangyu Yue, et al.
7

We propose to harness the potential of simulation for the semantic segmentation of real-world self-driving scenes in a domain generalization fashion. The segmentation network is trained without any data of target domains and tested on the unseen target domains. To this end, we propose a new approach of domain randomization and pyramid consistency to learn a model with high generalizability. First, we propose to randomize the synthetic images with the styles of real images in terms of visual appearances using auxiliary datasets, in order to effectively learn domain-invariant representations. Second, we further enforce pyramid consistency across different "stylized" images and within an image, in order to learn domain-invariant and scale-invariant features, respectively. Extensive experiments are conducted on the generalization from GTA and SYNTHIA to Cityscapes, BDDS and Mapillary; and our method achieves superior results over the state-of-the-art techniques. Remarkably, our generalization results are on par with or even better than those obtained by state-of-the-art simulation-to-real domain adaptation methods, which access the target domain data at training time.

READ FULL TEXT

page 1

page 3

page 7

03/03/2021

FSDR: Frequency Space Domain Randomization for Domain Generalization

Domain generalization aims to learn a generalizable model from a known s...
08/26/2019

Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach

We propose a new approach, called self-motivated pyramid curriculum doma...
08/05/2021

Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation

Semantic segmentation is a crucial image understanding task, where each ...
06/16/2022

Domain Generalization via Selective Consistency Regularization for Time Series Classification

Domain generalization methods aim to learn models robust to domain shift...
12/15/2020

Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation

Open compound domain adaptation (OCDA) is a domain adaptation setting, w...
10/13/2021

Do We Need to Directly Access the Source Datasets for Domain Generalization?

Domain generalization (DG) aims to learn a generalizable model from mult...
12/03/2018

VADRA: Visual Adversarial Domain Randomization and Augmentation

We address the issue of learning from synthetic domain randomized data e...

Code Repositories

DRPC

Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data (ICCV 2019)


view repo