Instance-level object segmentation is an important yet under-explored task. Most of state-of-the-art methods rely on region proposal methods to extract candidate segments and then utilize object classification to produce final results. Nonetheless, generating reliable region proposals itself is a quite challenging and unsolved task. In this work, we propose a Proposal-Free Network (PFN) to address the instance-level object segmentation problem, which outputs the numbers of instances of different categories and the pixel-level information on i) the coordinates of the instance bounding box each pixel belongs to, and ii) the confidences of different categories for each pixel, based on pixel-to-pixel deep convolutional neural network. All the outputs together, by using any off-the-shelf clustering method for simple post-processing, can naturally generate the ultimate instance-level object segmentation results. The whole PFN can be easily trained without the requirement of a proposal generation stage. Extensive evaluations on the challenging PASCAL VOC 2012 semantic segmentation benchmark demonstrate the effectiveness of the proposed PFN solution without relying on any proposal generation methods.

中文翻译：

---

实例级对象细分的无提案网络

实例级对象分段是一项重要但尚未充分研究的任务。大多数最先进的方法都依赖于区域提议方法来提取候选段，然后利用对象分类来产生最终结果。但是，生成可靠的区域建议本身是一项非常具有挑战性且尚未解决的任务。在这项工作中，我们提出了一个无提案网络（PFN）来解决实例级对象分割问题，该网络输出不同类别的实例数量以及i）实例边界框的坐标上的像素级信息。像素属于，并且ii）基于像素到像素的深度卷积神经网络，每个像素具有不同类别的置信度。通过使用任何现成的聚类方法来进行简单的后处理，所有输出结果加在一起，自然可以生成最终的实例级对象分割结果。整个PFN可以很容易地进行训练，而无需提案生成阶段。对具有挑战性的PASCAL VOC 2012语义分段基准的广泛评估证明了所提出的PFN解决方案的有效性，而无需依赖任何提案生成方法。