Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation
It addresses domain shift in semantic segmentation for computer vision applications, but is incremental as it builds on existing feature alignment methods.
The paper tackles unsupervised domain adaptation for semantic segmentation by maximizing cosine similarity between source and target domain features, achieving performance gains on GTA5→Cityscapes and SYNTHIA→Cityscapes tasks.
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$\to$ Cityscaspes and SYNTHIA$\to$ Cityscapes).