Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation - Supplementary Material - Hao Shi 1,3 Wei Feng 1,2

In our implementation, we adopt a warm-up strategy to pretrain the backbone network for 50,000 iterations. After the warm-up phase, we generate pseudo annotations for the training data in target domain and determine the initial values of category-key features based on source images. Next, we initialize the representative-key features and discrepancy features of each set in OLDM using a First-Input, Fist-Output (FIFO) queue. To ensure comprehensive initialization of all sets in OLDM, this phase extends over 4000 iterations. Upon completion, our method empowers the execution of Discrepancy Memorization and Style Compensation. In this section, we provide an extensive and comprehensive display of experiments.