以场景为中心的无监督全景分割
Scene-Centric Unsupervised Panoptic Segmentation
AI总结：
该研究针对无监督全景分割问题，提出首个直接基于以场景为中心图像训练的方法，结合视觉表示、深度和运动线索生成伪标签并采用自训练策略，在Cityscapes数据集上PQ指标较现有技术提升9.4个百分点。
摘要：
无监督全景分割旨在无需人工标注数据训练的情况下，将图像划分为语义有意义的区域和不同的对象实例。与之前关于无监督全景场景理解的工作相比，我们消除了对以对象为中心的训练数据的需求，从而实现对复杂场景的无监督理解。为此，我们提出首个直接在以场景为中心的图像上训练的无监督全景方法。具体而言，我们提出一种结合视觉表示、深度和运动线索的方法，以在复杂的以场景为中心的数据上获取高分辨率全景伪标签。利用伪标签训练和全景自训练策略，形成一种无需任何人工标注即可准确预测复杂场景全景分割的新方法。我们的方法显著提升全景质量，例如在Cityscapes数据集的无监督全景分割任务上，将最新技术水平的全景质量（PQ）提升了9.4个百分点。
英文摘要：
Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene understanding, we eliminate the need for object-centric training data, enabling the unsupervised understanding of complex scenes. To that end, we present the first unsupervised panoptic method that directly trains on scene-centric imagery. In particular, we propose an approach to obtain high-resolution panoptic pseudo labels on complex scene-centric data, combining visual representations, depth, and motion cues. Utilizing both pseudo-label training and a panoptic self-training strategy yields a novel approach that accurately predicts panoptic segmentation of complex scenes without requiring any human annotations. Our approach significantly improves panoptic quality, e.g., surpassing the recent state of the art in unsupervised panoptic segmentation on Cityscapes by 9.4% points in PQ.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
