AFRDA: Attentive Feature Refinement for Domain Adaptive Semantic Segmentation
This addresses segmentation errors in complex regions for domain adaptation tasks, but it is incremental as it builds on existing HRDA-based methods.
The paper tackled the problem of balancing local details and global context in unsupervised domain adaptive semantic segmentation by introducing the Adaptive Feature Refinement module, which improved segmentation accuracy by 1.05% mIoU on GTA V to Cityscapes and 1.04% mIoU on Synthia to Cityscapes.
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