Log In Sign Up

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

by   Rui Gong, et al.

Open compound domain adaptation (OCDA) is a domain adaptation setting, where target domain is modeled as a compound of multiple unknown homogeneous domains, which brings the advantage of improved generalization to unseen domains. In this work, we propose a principled meta-learning based approach to OCDA for semantic segmentation, MOCDA, by modeling the unlabeled target domain continuously. Our approach consists of four key steps. First, we cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner. Then, different sub-target domains are split into independent branches, for which batch normalization parameters are learnt to treat them independently. A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code. Meanwhile, we learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization. We validate the benefits of our approach by extensive experiments on synthetic-to-real knowledge transfer benchmark datasets, where we achieve the state-of-the-art performance in both compound and open domains.


page 1

page 7

page 9

page 16

page 17

page 18


DLOW: Domain Flow for Adaptation and Generalization

In this work, we propose a domain flow generation(DLOW) approach to mode...

Open Domain Generalization with Domain-Augmented Meta-Learning

Leveraging datasets available to learn a model with high generalization ...

ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation

In this paper, we present a direct adaptation strategy (ADAS), which aim...

Meta-Learned Feature Critics for Domain Generalized Semantic Segmentation

How to handle domain shifts when recognizing or segmenting visual data a...

Towards Generalization on Real Domain for Single Image Dehazing via Meta-Learning

Learning-based image dehazing methods are essential to assist autonomous...

Style-Guided Domain Adaptation for Face Presentation Attack Detection

Domain adaptation (DA) or domain generalization (DG) for face presentati...