Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation

03/02/2020
by   Myeongjin Kim, et al.
0

Since annotating pixel-level labels for semantic segmentation is laborious, leveraging synthetic data is an attractive solution. However, due to the domain gap between synthetic domain and real domain, it is challenging for a model trained with synthetic data to generalize to real data. In this paper, considering the fundamental difference between the two domains as the texture, we propose a method to adapt to the texture of the target domain. First, we diversity the texture of synthetic images using a style transfer algorithm. The various textures of generated images prevent a segmentation model from overfitting to one specific (synthetic) texture. Then, we fine-tune the model with self-training to get direct supervision of the target texture. Our results achieve state-of-the-art performance and we analyze the properties of the model trained on the stylized dataset with extensive experiments.

READ FULL TEXT

page 2

page 3

page 4

page 6

page 7

page 8

research
03/21/2023

Texture Learning Domain Randomization for Domain Generalized Segmentation

Deep Neural Networks (DNNs)-based semantic segmentation models trained o...
research
08/05/2021

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

Semantic segmentation is a crucial image understanding task, where each ...
research
10/24/2018

Learning color space adaptation from synthetic to real images of cirrus clouds

Training on synthetic data is becoming popular in vision due to the conv...
research
08/29/2019

Texture Underfitting for Domain Adaptation

Comprehensive semantic segmentation is one of the key components for rob...
research
07/16/2018

Effective Use of Synthetic Data for Urban Scene Semantic Segmentation

Training a deep network to perform semantic segmentation requires large ...
research
07/07/2018

One-shot Texture Segmentation

We introduce one-shot texture segmentation: the task of segmenting an in...
research
04/28/2020

Style-transfer GANs for bridging the domain gap in synthetic pose estimator training

Given the dependency of current CNN architectures on a large training se...

Please sign up or login with your details

Forgot password? Click here to reset