Segmenting unseen objects is a critical task in many different domains. For example, a robot may need to grasp an unseen object, which means it needs to visually separate this object from the background and/or other objects. Mean shift clustering is a common method in object segmentation tasks. However, the traditional mean shift clustering algorithm is not easily integrated into an end-to-end neural network training pipeline. In this work, we propose the Mean Shift Mask Transformer (MSMFormer), a new transformer architecture that simulates the von Mises-Fisher (vMF) mean shift clustering algorithm, allowing for the joint training and inference of both the feature extractor and the clustering. Its central component is a hypersphere attention mechanism, which updates object queries on a hypersphere. To illustrate the effectiveness of our method, we apply MSMFormer to Unseen Object Instance Segmentation, which yields a new state-of-the-art of 87.3 Boundary F-meansure on the real-world Object Clutter Indoor Dataset (OCID). Code is available at https://github.com/YoungSean/UnseenObjectsWithMeanShift

该研究提出了一个新型变压器结构MSMFormer，它模拟vMF均值漂移聚类算法，从而允许联合训练和推理特征提取器和聚类器。通过将该方法应用于未见物体实例分割，可以得到新的最先进效果，并且可以在OCID真实世界对象杂乱室内数据集上获得87.3边界F值。

针对未见过物体实例分割的均值漂移遮罩变换器