Semantic segmentation aims to predict pixel-level labels. It has become a popular task in various computer vision applications. While fully supervised segmentation methods have achieved high accuracy on large-scale vision datasets, they are unable to generalize on a new test environment or a new domain well. In this work, we first introduce a new Un-aligned Domain Score to measure the efficiency of a learned model on a new target domain in unsupervised manner. Then, we present the new Bijective Maximum Likelihood(BiMaL) loss that is a generalized form of the Adversarial Entropy Minimization without any assumption about pixel independence. We have evaluated the proposed BiMaL on two domains. The proposed BiMaL approach consistently outperforms the SOTA methods on empirical experiments on "SYNTHIA to Cityscapes", "GTA5 to Cityscapes", and "SYNTHIA to Vistas".
@article{arxiv.2108.03267,
title = {BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation},
author = {Thanh-Dat Truong and Chi Nhan Duong and Ngan Le and Son Lam Phung and Chase Rainwater and Khoa Luu},
journal= {arXiv preprint arXiv:2108.03267},
year = {2021}
}