COCONut：对COCO分割任务的现代化升级
COCONut: Modernizing COCO Segmentation
AI总结：
针对COCO分割基准标注粗糙、不同分割类型标注不一致的问题，研究团队推出含38.3万张图像、超518万高质量全景掩码的COCONut数据集，统一三类分割标注，构建经人工验证的大规模通用分割基准。
摘要：
近几十年来，视觉领域的视觉识别技术取得了显著进展，部分得益于数据集基准的发展。其中，成熟的COCO基准推动了现代检测与分割系统的研发。但过去十年间，COCO分割基准的改进相对缓慢。该基准最初仅为物体（thing）实例配备粗略的多边形标注，后逐步加入了针对素材（stuff）区域的粗略超像素标注，这些标注随后通过启发式方法合并，生成全景分割标注。这些标注由不同的标注团队完成，不仅导致分割掩码较为粗糙，还造成了不同分割类型之间的不一致性。本研究对COCO分割标注开展了全面的重新评估。我们通过提升标注质量，并将数据集扩展至包含38.3万张图像、超518万个全景掩码，推出了COCONut——即COCO Next Universal segmenTation（COCO下一代通用分割）数据集。COCONut统一了语义分割、实例分割与全景分割的标注，配备精心制作的高质量掩码，为所有分割任务构建了可靠的基准。据我们所知，COCONut是首个经过人工标注者验证的大规模通用分割数据集。我们预计COCONut的发布将极大提升社区评估新型神经网络进展的能力。
英文摘要：
In recent decades, the vision community has witnessed remarkable progress in visual recognition, partially owing to advancements in dataset benchmarks. Notably, the established COCO benchmark has propelled the development of modern detection and segmentation systems. However, the COCO segmentation benchmark has seen comparatively slow improvement over the last decade. Originally equipped with coarse polygon annotations for thing instances, it gradually incorporated coarse superpixel annotations for stuff regions, which were subsequently heuristically amalgamated to yield panoptic segmentation annotations. These annotations, executed by different groups of raters, have resulted not only in coarse segmentation masks but also in inconsistencies between segmentation types. In this study, we undertake a comprehensive reevaluation of the COCO segmentation annotations. By enhancing the annotation quality and expanding the dataset to encompass 383K images with more than 5.18M panoptic masks, we introduce COCONut, the COCO Next Universal segmenTation dataset. COCONut harmonizes segmentation annotations across semantic, instance, and panoptic segmentation with meticulously crafted high-quality masks, and establishes a robust benchmark for all segmentation tasks. To our knowledge, COCONut stands as the inaugural large-scale universal segmentation dataset, verified by human raters. We anticipate that the release of COCONut will significantly contribute to the community's ability to assess the progress of novel neural networks.
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。
