去噪与对齐：面向鲁棒全景语义分割的无源无监督域自适应
Denoise and Align: Towards Source-Free UDA for Robust Panoramic Semantic Segmentation
针对全景分割中的几何畸变和域偏移，提出无源域自适应框架，通过置信度引导的伪标签去噪和跨分辨率对抗对齐来提升伪标签质量与类别平衡性，可直接复用于其他密集预测任务的无源域自适应场景。
原文依据 DAPASS introduces two synergistic modules to robustly transfer knowledge without source data.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论全景语义分割对于自动驾驶和虚拟现实等关键应用中的全面360度场景理解至关重要。然而，该领域的进展受到两个关键挑战的制约：全景投影中固有的严重几何畸变以及密集标注的高昂成本。虽然从标签丰富的针孔相机数据集进行无监督域自适应（UDA）提供了一种可行的替代方案，但许多现实世界任务施加了更严格的無源（SFUDA）约束，即由于隐私或专有原因无法访问源数据。这一约束显著放大了域偏移的核心问题，导致伪标签不可靠和性能急剧下降，尤其是对于少数类别。为了克服这些限制，我们提出了DAPASS框架。DAPASS引入了两个协同模块，以在没有源数据的情况下稳健地迁移知识。首先，我们的全景置信度引导去噪（PCGD）模块通过强制扰动一致性并结合邻域级置信度来过滤噪声，从而生成高保真、类别平衡的伪标签。其次，上下文分辨率对抗模块（CRAM）通过将高分辨率裁剪的细粒度细节与低分辨率上下文的全局语义进行对抗对齐，明确解决了尺度变化和畸变问题。DAPASS在室外（Cityscapes到DensePASS）和室内（Stanford2D3D）基准上取得了最优性能，分别达到55.04%（+2.05%）和70.38%（+1.54%）的mIoU。
英文原文摘要 1577 字符
Panoramic semantic segmentation is pivotal for comprehensive 360deg scene understanding in critical applications like autonomous driving and virtual reality. However, progress in this domain is constrained by two key challenges: the severe geometric distortions inherent in panoramic projections and the prohibitive cost of dense annotation. While Unsupervised Domain Adaptation (UDA) from label-rich pinhole-camera datasets offers a viable alternative, many real-world tasks impose a stricter source-free (SFUDA) constraint where source data is inaccessible for privacy or proprietary reasons. This constraint significantly amplifies the core problems of domain shift, leading to unreliable pseudo-labels and dramatic performance degradation, particularly for minority classes. To overcome these limitations, we propose the DAPASS framework. DAPASS introduces two synergistic modules to robustly transfer knowledge without source data. First, our Panoramic Confidence-Guided Denoising (PCGD) module generates high-fidelity, class-balanced pseudo-labels by enforcing perturbation consistency and incorporating neighborhood-level confidence to filter noise. Second, a Contextual Resolution Adversarial Module (CRAM) explicitly addresses scale variance and distortion by adversarially aligning fine-grained details from high-resolution crops with global semantics from low-resolution contexts. DAPASS achieves state-of-the-art performances on outdoor (Cityscapes-to-DensePASS) and indoor (Stanford2D3D) benchmarks, yielding 55.04% (+2.05%) and 70.38% (+1.54%) mIoU, respectively.