Segmentation is a core computer vision competency, with applications spanning a broad range of scientifically and economically valuable domains. To date, however, the prohibitive cost of annotation has limited the deployment of flexible segmentation models. In this work, we propose Zero-shot Unsupervised Transfer Instance Segmentation (ZUTIS), a framework that aims to meet this challenge. The key strengths of ZUTIS are: (i) no requirement for instance-level or pixel-level annotations; (ii) an ability of zero-shot transfer, i.e., no assumption on access to a target data distribution; (iii) a unified framework for semantic and instance segmentations with solid performance on both tasks compared to state-of-the-art unsupervised methods. While comparing to previous work, we show ZUTIS achieves a gain of 2.2 mask AP on COCO-20K and 14.5 mIoU on ImageNet-S with 919 categories for instance and semantic segmentations, respectively. The code is made publicly available.

翻译：分割是计算机视觉的核心能力，其应用涵盖广泛且具有重要科学价值和经济价值的领域。然而，迄今为止，高昂的标注成本限制了灵活分割模型的部署。本文提出零样本无监督迁移实例分割（ZUTIS）框架，旨在应对这一挑战。ZUTIS的关键优势在于：(i) 无需实例级或像素级标注；(ii) 具备零样本迁移能力，即不假设能访问目标数据分布；(iii) 提供语义分割与实例分割的统一框架，且与现有最先进无监督方法相比，在两项任务上均展现出稳健性能。与先前工作对比表明，ZUTIS在COCO-20K数据集上实例分割的掩膜AP提升2.2，在ImageNet-S数据集上语义分割的mIoU提升14.5（覆盖919个类别）。相关代码已公开。