BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
This addresses the challenge of generalizing semantic segmentation models to new domains without labeled data, which is crucial for real-world applications like autonomous driving, though it appears incremental as it builds on adversarial entropy minimization.
The paper tackles the problem of domain adaptation in semantic segmentation by introducing a new Bijective Maximum Likelihood loss, which outperforms state-of-the-art methods on benchmarks like SYNTHIA to Cityscapes with consistent empirical gains.
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".