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

by   Inseop Chung, et al.

We propose a novel method that tackles the problem of unsupervised domain adaptation for semantic segmentation by maximizing the cosine similarity between the source and the target domain at the feature level. A segmentation network mainly consists of two parts, a feature extractor and a classification head. We expect that if we can make the two domains have small domain gap at the feature level, they would also have small domain discrepancy at the classification head. Our method computes a cosine similarity matrix between the source feature map and the target feature map, then we maximize the elements exceeding a threshold to guide the target features to have high similarity with the most similar source feature. Moreover, we use a class-wise source feature dictionary which stores the latest features of the source domain to prevent the unmatching problem when computing the cosine similarity matrix and be able to compare a target feature with various source features from various images. Through extensive experiments, we verify that our method gains performance on two unsupervised domain adaptation tasks (GTA5→ Cityscaspes and SYNTHIA→ Cityscapes).


page 1

page 3

page 8

page 12


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...

Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching

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

Attention-based Cross-Layer Domain Alignment for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) aims to learn transferable knowledg...

Integrating Categorical Semantics into Unsupervised Domain Translation

While unsupervised domain translation (UDT) has seen a lot of success re...

Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings

Deep learning frameworks allowed for a remarkable advancement in semanti...

Multi-step Online Unsupervised Domain Adaptation

In this paper, we address the Online Unsupervised Domain Adaptation (OUD...

Domain Adaptation on Semantic Segmentation with Separate Affine Transformation in Batch Normalization

In recent years, unsupervised domain adaptation (UDA) for semantic segme...

Code Repositories