In this paper, we introduce VoteCut, an innovative method for unsupervised object discovery that leverages feature representations from multiple self-supervised models. VoteCut employs normalized-cut based graph partitioning, clustering and a pixel voting approach. Additionally, We present CuVLER (Cut-Vote-and-LEaRn), a zero-shot model, trained using pseudo-labels, generated by VoteCut, and a novel soft target loss to refine segmentation accuracy. Through rigorous evaluations across multiple datasets and several unsupervised setups, our methods demonstrate significant improvements in comparison to previous state-of-the-art models. Our ablation studies further highlight the contributions of each component, revealing the robustness and efficacy of our approach. Collectively, VoteCut and CuVLER pave the way for future advancements in image segmentation.

翻译：在本文中，我们提出VoteCut——一种创新的无监督目标发现方法，它利用多个自监督模型的特征表示。VoteCut采用基于归一化切割的图分割、聚类和像素投票方法。此外，我们提出CuVLER（Cut-Vote-and-LEaRn），这是一种零样本模型，使用VoteCut生成的伪标签和新型软目标损失函数进行训练，以优化分割精度。通过在多个数据集和多种无监督设置下的严格评估，我们的方法相比先前最先进模型展现出显著改进。消融研究进一步突出了各组成部分的贡献，揭示了方法的鲁棒性和有效性。总体而言，VoteCut和CuVLER为图像分割的未来发展铺平了道路。