Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation

09/16/2022
by   Lin Chen, et al.
3

In unsupervised domain adaptation (UDA), directly adapting from the source to the target domain usually suffers significant discrepancies and leads to insufficient alignment. Thus, many UDA works attempt to vanish the domain gap gradually and softly via various intermediate spaces, dubbed domain bridging (DB). However, for dense prediction tasks such as domain adaptive semantic segmentation (DASS), existing solutions have mostly relied on rough style transfer and how to elegantly bridge domains is still under-explored. In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for DASS, through which the joint distributions of source and target domains are aligned and interacted with each in the intermediate space. At the heart of DDB lies a dual-path domain bridging step for generating two intermediate domains using the coarse-wise and the fine-wise data mixing techniques, alongside a cross-path knowledge distillation step for taking two complementary models trained on generated intermediate samples as 'teachers' to develop a superior 'student' in a multi-teacher distillation manner. These two optimization steps work in an alternating way and reinforce each other to give rise to DDB with strong adaptation power. Extensive experiments on adaptive segmentation tasks with different settings demonstrate that our DDB significantly outperforms state-of-the-art methods. Code is available at https://github.com/xiaoachen98/DDB.git.

READ FULL TEXT

page 2

page 5

page 7

page 15

research
09/26/2020

Affinity Space Adaptation for Semantic Segmentation Across Domains

Semantic segmentation with dense pixel-wise annotation has achieved exce...
research
07/20/2021

DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation

Unsupervised domain adaptation (UDA) for semantic segmentation aims to a...
research
08/13/2021

Dual Path Learning for Domain Adaptation of Semantic Segmentation

Domain adaptation for semantic segmentation enables to alleviate the nee...
research
07/11/2022

Gradual Domain Adaptation without Indexed Intermediate Domains

The effectiveness of unsupervised domain adaptation degrades when there ...
research
08/05/2021

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

Unsupervised domain adaptive person re-identification (UDA re-ID) aims a...
research
11/19/2021

Bi-Mix: Bidirectional Mixing for Domain Adaptive Nighttime Semantic Segmentation

In autonomous driving, learning a segmentation model that can adapt to v...
research
03/15/2022

Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation

After the great success of Vision Transformer variants (ViTs) in compute...

Please sign up or login with your details

Forgot password? Click here to reset