Distinguishing foreground and background alignment for unsupervised domain adaptative semantic segmentation

Unsupervised domain adaptive semantic segmentation uses the knowledge learned from the labeled source domain dataset to guide the segmentation of the target domain. However, this domain migration method will cause a large inter-domain difference due to the different feature distributions between the source domain and the target domain. We use the self-supervised learning method to generate pseudo labels for the target domain, so that the corresponding pixels are directly aligned with the source domain according to the segmentation loss. Through observation, it is found that the spatial distribution of the background class in the source domain and the target domain has a small difference, and the appearance of the same class of the foreground class will also be quite different. We use the method of distinguishing alignment between foreground and background classes. We understand that acquiring the rich space and channel information on the feature map during the convolution process is essential for fine-grained semantic segmentation. Therefore, in order to obtain the dependency relationship between the channels of the feature map and the spatial position information, we use a channel and spatial parallel attention module. This module enables the network to select and amplify valuable space and channel information from the global information and suppress useless information. In addition, we introduce focal loss to solve the problem of class imbalance in the data set. Experiments show that our method achieves better segmentation performance in unsupervised domain adaptive semantic segmentation. (c) 2022 Elsevier B.V. All rights reserved.

Automated summary

Unsupervised domain adaptive semantic segmentation utilizes knowledge learned from labeled source domain dataset to guide segmentation in the target domain. Pseudo labels are generated using a self-supervised learning method to align corresponding pixels with the source domain based on segmentation loss. A channel and spatial parallel attention module is employed to extract rich spatial and channel information from the feature map, and focal loss is introduced to address class imbalance in the dataset.