Unsupervised image-to-image (I2I) translation learns cross-domain image
mapping that transfers input from the source domain to output in the target
domain while preserving its semantics. One challenge is that different semantic
statistics in source and target domains result in content discrepancy known as
semantic distortion. To address this problem, a novel I2I method that maintains
semantic consistency in translation is proposed and named SemST in this work.
SemST reduces semantic distortion by employing contrastive learning and
aligning the structural and textural properties of input and output by
maximizing their mutual information. Furthermore, a multi-scale approach is
introduced to enhance translation performance, thereby enabling the
applicability of SemST to domain adaptation in high-resolution images.
Experiments show that SemST effectively mitigates semantic distortion and
achieves state-of-the-art performance. Also, the application of SemST to domain
adaptation (DA) is explored. It is demonstrated by preliminary experiments that
SemST can be utilized as a beneficial pre-training for the semantic
segmentation task.

通过对比学习和对齐输入和输出的结构和纹理特性，提出了一种名为 SemST 的新型 I2I 方法，用于在保持语义的同时实现语义无损的领域内图像映射，进一步引入多尺度方法增强翻译性能，适用于高分辨率图像领域适应。实验证明，SemST 可以有效减少语义失真，并取得了最先进的性能，同时还探讨了 SemST 应用于领域适应的可能性，初步实验表明 SemST 可作为语义分割任务的有益预训练。