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

by   Zhonghao Wang, et al.

We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work. State-of-the-art approaches prove that performing semantic-level alignment is helpful in tackling the domain shift issue. Based on the observation that stuff categories usually share similar appearances across images of different domains while things (i.e. object instances) have much larger differences, we propose to improve the semantic-level alignment with different strategies for stuff regions and for things: 1) for the stuff categories, we generate feature representation for each class and conduct the alignment operation from the target domain to the source domain; 2) for the thing categories, we generate feature representation for each individual instance and encourage the instance in the target domain to align with the most similar one in the source domain. In this way, the individual differences within thing categories will also be considered to alleviate over-alignment. In addition to our proposed method, we further reveal the reason why the current adversarial loss is often unstable in minimizing the distribution discrepancy and show that our method can help ease this issue by minimizing the most similar stuff and instance features between the source and the target domains. We conduct extensive experiments in two unsupervised domain adaptation tasks, i.e. GTA5 to Cityscapes and SYNTHIA to Cityscapes, and achieve the new state-of-the-art segmentation accuracy.


page 1

page 3

page 8


Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation

Unsupervised domain adaptation (UDA) aims to enhance the generalization ...

Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching

Unsupervised domain adaptation for point cloud semantic segmentation has...

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

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

Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation

We propose a novel method that tackles the problem of unsupervised domai...

More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation

Feature alignment between domains is one of the mainstream methods for U...

Spatial Attention Pyramid Network for Unsupervised Domain Adaptation

Unsupervised domain adaptation is critical in various computer vision ta...

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

We consider the problem of unsupervised domain adaptation in semantic se...

Please sign up or login with your details

Forgot password? Click here to reset