MC-PanDA++：更简单、更强、更鲁棒的域自适应全景分割
MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentation
浏览论文内容
中文总结 AI 辅助
MC-PanDA++通过自监督编码器、逐类自适应损失缩放和单阶段训练，简化并增强了域自适应全景分割，提升了性能与鲁棒性。
中文摘要 AI 辅助
无监督域自适应（UDA）通过利用成本效益高的带标签源域（如合成数据）和未标记的目标域来弥合分布差距，从而减少全景分割中的标注负担。现有的全景UDA方法依赖于基于次优的逐像素分割架构的师生一致性学习。相比之下，最先进的掩码变换器很少被采用，因为它们在一致性学习中对确认偏差表现出明显的脆弱性，即训练过程中错误的教师预测会被强化。我们之前的方法MC-PanDA通过细粒度的置信度估计缓解了这一问题，该估计抑制了来自不可靠掩码的梯度，同时采样信息丰富且可靠的损失计算位置。然而，该方法需要复杂的多阶段训练和仔细的超参数调整。本文提出了MC-PanDA++，通过引入以下内容来解决这些限制：（i）自监督视觉编码器，提供更强、更鲁棒的初始化，进一步减少对人类标注的依赖；（ii）逐类、自适应掩码级损失缩放，稳定训练并允许跨域使用单一超参数集；（iii）单阶段训练流程，降低整体概念复杂性。这些改进共同产生了一种概念上更简单、性能更好、更鲁棒的域自适应全景分割方法。源代码：此https URL
英文摘要
Unsupervised domain adaptation (UDA) reduces the annotation burden in panoptic segmentation by leveraging a cost-effectively labeled source domain (e.g., synthetic) and an unlabeled target domain to bridge the distribution gap. Existing panoptic UDA methods rely on teacher-student consistency learning built upon suboptimal per-pixel segmentation architectures. In contrast, state-of-the-art mask transformers are rarely adopted due to their pronounced vulnerability to confirmation bias in consistency learning, where erroneous teacher predictions are reinforced during training. Our earlier approach, MC-PanDA, mitigates this issue through fine-grained confidence estimation, which suppresses gradients from unreliable masks while sampling informative yet reliable locations for loss computation. However, this method entails a complex multi-stage training and requires careful hyperparameter tuning. This work presents MC-PanDA++, which addresses these limitations by introducing: (i) self-supervised vision encoders that provide a stronger and more robust initialization, further reducing the reliance on human annotations, (ii) per-class, self-adapting mask-wide loss scaling that stabilizes training and enables the usage of a single set of hyperparameters across domains, and (iii) a single-stage training pipeline that decreases overall conceptual complexity. Together, these improvements result in a conceptually simpler, better-performing, and more robust method for domain-adaptive panoptics. Source code: https://github.com/martinovicivan/MC-PanDA
发表机构
- Faculty of Electrical Engineering and Computing, University of Zagreb（萨格勒布大学电气工程与计算学院）
- Faculty of Computer and Information Science, University of Ljubljana（卢布尔雅那大学计算机与信息科学学院）
- Fundamental AI Lab, University of Technology Nuremberg（纽伦堡工业大学基础人工智能实验室）
机构由 AI 辅助整理，请以论文原文为准。
