Domain Adaptation on Semantic Segmentation with Separate Affine Transformation in Batch Normalization

TL;DR

This paper introduces a simple, effective modification to Batch Normalization called Separate Affine Transformation (SEAT) for unsupervised domain adaptation in semantic segmentation, enhancing adaptation without added complexity.

Contribution

It proposes SEAT, a novel affine transformation in Batch Normalization, and a multi-level feature adaptation method that improve UDA performance with less complexity.

Findings

SEAT improves domain adaptation performance.

Multi-level feature adaptation enhances segmentation accuracy.

Method maintains simplicity while matching complex models.

Abstract

In recent years, unsupervised domain adaptation (UDA) for semantic segmentation has brought many researchers'attention. Many of them take an approach to design a complex system so as to better align the gap between source and target domain. Instead, we focus on the very basic structure of the deep neural network, Batch Normalization, and propose to replace the Sharing Affine Transformation with our proposed Separate Affine Transformation (SEAT). The proposed SEAT is simple, easily implemented and easy to integrate into existing adversarial learning based UDA methods. Also, to further improve the adaptation quality, we introduce multi level adaptation by adding the lower-level features to the higher-level ones before feeding them to the discriminator, without adding extra discriminator like others. Experiments show that the proposed methods is less complex without losing performance accuracy when compared with other UDA methods.