论文标题
深度变分实例细分
Deep Variational Instance Segmentation
论文作者
论文摘要
实例细分旨在在输入图像中获得每个像素的类和实例标签，这是计算机视觉中的一项艰巨任务。最先进的算法通常采用两个单独的阶段，第一个生成对象建议，第二个阶段是识别和完善边界的第二个阶段。此外，建议通常基于探测器，例如更快的R-CNN，该探测器详尽地搜索了整个图像中的框。在本文中，我们提出了一种新型算法，该算法直接利用完全卷积网络（FCN）来预测实例标签。具体而言，我们提出了实例分割的变分放松，以最大程度地降低分段构分段问题的优化功能，该功能可用于训练FCN端到端。它扩展了经典的Mumford-Shah变分段问题，以便能够在实例分割的基础真理中处理置换不变标签。 Pascal VOC 2012，语义边界数据集（SBD）和MSCOCO 2017数据集的实验表明，所提出的方法有效地解决了实例细分任务。源代码和训练有素的模型将与纸张一起发布。
Instance Segmentation, which seeks to obtain both class and instance labels for each pixel in the input image, is a challenging task in computer vision. State-of-the-art algorithms often employ two separate stages, the first one generating object proposals and the second one recognizing and refining the boundaries. Further, proposals are usually based on detectors such as faster R-CNN which search for boxes in the entire image exhaustively. In this paper, we propose a novel algorithm that directly utilizes a fully convolutional network (FCN) to predict instance labels. Specifically, we propose a variational relaxation of instance segmentation as minimizing an optimization functional for a piecewise-constant segmentation problem, which can be used to train an FCN end-to-end. It extends the classical Mumford-Shah variational segmentation problem to be able to handle permutation-invariant labels in the ground truth of instance segmentation. Experiments on PASCAL VOC 2012, Semantic Boundaries dataset(SBD), and the MSCOCO 2017 dataset show that the proposed approach efficiently tackle the instance segmentation task. The source code and trained models will be released with the paper.
