Class-agnostic object proposal generation is an important first step in many object detection pipelines. However, object proposals of modern systems are rather inaccurate in terms of segmentation and only roughly adhere to object boundaries. Since typical refinement steps are usually not applicable to thousands of proposals, we propose a superpixel-based refinement system for object proposal generation systems. Utilizing precise superpixels and superpixel pooling on deep features, we refine initial coarse proposals in an end-to-end learned system. Furthermore, we propose a novel DeepFH segmentation, which enriches the classic Felzenszwalb and Huttenlocher (FH) segmentation with deep features leading to improved segmentation results and better object proposal refinements. On the COCO dataset with LVIS annotations, we show that our refinement based on DeepFH superpixels outperforms state-of-the-art methods and leads to more precise object proposals.

与类别无关的对象提议生成是许多对象检测管道中重要的第一步。然而，现代系统的对象提议在分割方面相当不准确，并且只能粗略地遵守对象边界。由于典型的细化步骤通常不适用于数千个提案，因此我们为对象提案生成系统提出了一个基于超像素的细化系统。利用深度特征上的精确超像素和超像素池化，我们在端到端学习系统中细化初始粗提议。此外，我们提出了一种新颖的 DeepFH 分割，它通过深度特征丰富了经典的 Felzenszwalb 和 Huttenlocher (FH) 分割，从而改善了分割结果和更好的对象提议细化。在带有 LVIS 标注的 COCO 数据集上，