arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.07682cs.CV
收藏

基于点监督的全景分割全卷积网络

Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision

The Chinese University of Hong Kong(香港中文大学);University of Oxford(牛津大学);The University of Hong Kong(香港大学);MEGVII Technology(旷视科技)

Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Yukang Chen, Lu Qi, Liwei Wang, Zeming Li, Jian Sun, Jiaya Jia

摘要:

在本文中,我们提出了一个概念上简单,强大,有效的框架,充分和弱监督全景分割,称为Panoptic FCN。我们的方法旨在在一个统一的完全卷积管道中表示和预测前景事物和背景事物,可以通过基于点的完全或弱监督进行优化。特别地,Panoptic FCN使用所提出的核生成器对每个对象实例或填充物类别进行编码,并通过直接卷积高分辨率特征来产生预测。通过这种方法,可以在一个简单的生成内核然后分段的工作流中分别满足事物和材料的实例感知和语义一致的属性。该方法不需要额外的盒子来进行本地化或实例分离,比以前的基于盒子和无盒子的模型具有更高的效率。此外,我们提出了一种新形式的基于点的弱监督全景分割的注释。它只需要几个随机点的东西,这大大降低了人工标注成本。所提出的Panoptic FCN也被证明在这种弱监督设置中具有更优越的性能,其实现了82%的全监督性能,每个实例仅具有20个随机注释点。大量的实验证明了Panoptic FCN在COCO,VOC 2012,Cityscapes和Mapillary Vistas数据集上的有效性和效率。它为全监督和弱监督全景分割建立了一个新的领先基准。我们的代码和模型在https://github.com/dvlab-research/PanopticFCN上公开提供。

英文摘要:

In this paper, we present a conceptually simple, strong, and efficient framework for fully- and weakly-supervised panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff in a unified fully convolutional pipeline, which can be optimized with point-based fully or weak supervision. In particular, Panoptic FCN encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly. With this approach, instance-aware and semantically consistent properties for things and stuff can be respectively satisfied in a simple generate-kernel-then-segment workflow. Without extra boxes for localization or instance separation, the proposed approach outperforms the previous box-based and -free models with high efficiency. Furthermore, we propose a new form of point-based annotation for weakly-supervised panoptic segmentation. It only needs several random points for both things and stuff, which dramatically reduces the annotation cost of human. The proposed Panoptic FCN is also proved to have much superior performance in this weakly-supervised setting, which achieves 82% of the fully-supervised performance with only 20 randomly annotated points per instance. Extensive experiments demonstrate the effectiveness and efficiency of Panoptic FCN on COCO, VOC 2012, Cityscapes, and Mapillary Vistas datasets. And it sets up a new leading benchmark for both fully- and weakly-supervised panoptic segmentation. Our code and models are made publicly available at https://github.com/dvlab-research/PanopticFCN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑