BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation

Autor:	Truong, Thanh-Dat, Duong, Chi Nhan, Le, Ngan, Phung, Son Lam, Rainwater, Chase, Luu, Khoa
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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". Comment: Accepted to ICCV 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2108.03267 Zobrazit plný text záznamu View this record from Arxiv