AFRDA：面向领域自适应语义分割的注意力特征精炼

摘要

在无监督领域自适应语义分割（UDA-SS）中，模型首先在有标注的源域数据（如合成图像）上进行训练，随后无需目标域标注即可适应于无标注的目标域（如真实世界图像）。现有的UDA-SS方法往往难以在细粒度局部细节与全局上下文信息之间取得平衡，导致在复杂区域出现分割错误。为解决这一问题，我们提出了自适应特征精炼（AFR）模块，该模块通过利用低分辨率logits的语义先验来精炼高分辨率特征，从而提升分割精度。AFR还整合了高频成分，这些成分捕捉了细粒度结构并提供了关键的边界信息，改善了物体轮廓的描绘。此外，AFR通过不确定性驱动的注意力机制自适应地平衡局部与全局信息，减少了误分类。其轻量化设计使其能够无缝集成到基于HRDA的UDA方法中，实现了最先进的分割性能。我们的方法在GTA V转Cityscapes任务上将现有UDA-SS方法提升了1.05%的mIoU，在Synthia转Cityscapes任务上提升了1.04%的mIoU。我们的框架实现已发布于：https://github.com/Masrur02/AFRDA。

English

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

AFRDA：面向领域自适应语义分割的注意力特征精炼

AFRDA: Attentive Feature Refinement for Domain Adaptive Semantic Segmentation

摘要

Support