177d68f4adef163b7b123b5c5adb3c60-Supplemental-Conference.pdf

Following [2], we extend our method into multi-domain translation on AFHQ dataset, where the source domain includes Cat and Wild and the target domain is Dog. In this setting, similar to two-domain unpaired I2I, the EGSDE also employs an energy function pretrained on both the source and target domains to guide the inference process of a pretrained SDE. The only difference is the domain-specific feature extractor Es(,) involved in the energy function is the all but the last eliminate layer of randomness.