AFRDA: Attentive Feature Refinement for Domain Adaptive Semantic Segmentation

TL;DR

This paper introduces AFRDA, a novel module that refines features using semantic priors and high-frequency details to improve unsupervised domain adaptive semantic segmentation, achieving state-of-the-art results.

Contribution

The paper presents the AFR module, which enhances segmentation by refining features with semantic priors and high-frequency components, and integrates it into existing UDA methods for improved accuracy.

Findings

Achieved 1.05% mIoU improvement on GTA V to Cityscapes

Achieved 1.04% mIoU improvement on Synthia to Cityscapes

Demonstrated effective integration with HRDA-based UDA methods

Abstract

In Unsupervised Domain Adaptive Semantic Segmentation (UDA-SS), a model is trained on labeled source domain data (e.g., synthetic images) and adapted to an unlabeled target domain (e.g., real-world images) without access to target annotations. Existing UDA-SS methods often struggle to balance fine-grained local details with global contextual information, leading to segmentation errors in complex regions. To address this, we introduce the Adaptive Feature Refinement (AFR) module, which enhances segmentation accuracy by refining highresolution features using semantic priors from low-resolution logits. AFR also integrates high-frequency components, which capture fine-grained structures and provide crucial boundary information, improving object delineation. Additionally, AFR adaptively balances local and global information through uncertaintydriven attention, reducing misclassifications. Its lightweight design allows seamless integration into HRDA-based UDA methods, leading to state-of-the-art segmentation performance. Our approach improves existing UDA-SS methods by 1.05% mIoU on GTA V --> Cityscapes and 1.04% mIoU on Synthia-->Cityscapes. The implementation of our framework is available at: https://github.com/Masrur02/AFRDA