Abstract
This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation methods requires annotation masks for all object instances, which is expensive to acquire or even infeasible in some realistic scenarios, where the number of categories may increase boundlessly. In this paper, we present a novel open-set semantic instance segmentation approach capable of segmenting all known and unknown object classes in images, based on the output of an object detector trained on known object classes. We formulate the problem using a Bayesian framework, where the posterior distribution is approximated with a simulated annealing optimization equipped with an efficient image partition sampler. We show empirically that our method is competitive with state-of-the-art supervised methods on known classes, but also performs well on unknown classes when compared with unsupervised methods.
Abstract (translated)
本文讨论了开放条件下的语义实例分割任务,其中输入图像可以包含已知和未知的对象类。现有语义实例分割方法的训练过程需要所有对象实例的注释掩模,这在某些现实场景中获取或甚至是不可行的,其中类别的数量可能无限增加。在本文中,我们提出了一种新颖的开放式语义实例分割方法,该方法能够基于在已知对象类上训练的对象检测器的输出来分割图像中的所有已知和未知对象类。我们使用贝叶斯框架来制定问题,其中后验分布用配备有效图像分区采样器的模拟退火优化来近似。我们凭经验证明,我们的方法与已知类的最先进的监督方法相比具有竞争力,但与无监督方法相比,它在未知类上也表现良好。
URL
https://arxiv.org/abs/1806.00911