Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation

by   Yawei Luo, et al.

We consider the problem of unsupervised domain adaptation in semantic segmentation, in which the source domain is fully annotated, and the target domain is unlabeled. The key in this campaign consists in reducing the domain shift, i.e., enforcing the data distributions of the two domains to be similar. A popular strategy is to align the marginal distribution in the feature space through adversarial learning. However, this global alignment strategy does not consider the local category-level feature distribution. A possible consequence of the global movement is that some categories which are originally well aligned between the source and target may be incorrectly mapped. To address this problem, this paper introduces a category-level adversarial network, aiming to enforce local semantic consistency during the trend of global alignment. Our idea is to take a close look at the category-level data distribution and align each class with an adaptive adversarial loss. Specifically, we reduce the weight of the adversarial loss for category-level aligned features while increasing the adversarial force for those poorly aligned. In this process, we decide how well a feature is category-level aligned between source and target by a co-training approach. In two domain adaptation tasks, i.e., GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, we validate that the proposed method matches the state of the art in segmentation accuracy.


page 5

page 8


Unsupervised Domain Adaptive Fundus Image Segmentation with Category-level Regularization

Existing unsupervised domain adaptation methods based on adversarial lea...

Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation

We consider the problem of unsupervised domain adaptation for semantic s...

Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation

Recent advances in unsupervised domain adaptation for semantic segmentat...

Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation

Learning segmentation from synthetic data and adapting to real data can ...

Self-adaptive Re-weighted Adversarial Domain Adaptation

Existing adversarial domain adaptation methods mainly consider the margi...

Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation

For unsupervised domain adaptation problems, the strategy of aligning th...

An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation

We focus on Unsupervised Domain Adaptation (UDA) for the task of semanti...

Please sign up or login with your details

Forgot password? Click here to reset