论文标题
Disir：深层图像分割，并进行交互式精致
DISIR: Deep Image Segmentation with Interactive Refinement
论文作者
论文摘要
本文提出了一种用于空中图像的多类分割的交互式方法。确切地说，它基于一个深度神经网络，该网络利用了RGB图像和注释。从仅基于图像的初始输出开始，我们的网络然后使用图像和用户注释的串联进行交互性地完善该分割图。重要的是，用户注释会修改网络的输入（而不是其权重），从而实现了快速而平滑的过程。通过在两个公共空中数据集上的实验，我们表明用户注释非常有意义：每次点击纠正大约5000像素。我们分析了框架各个方面的影响，例如注释的表示，培训数据的数量或网络体系结构。代码可在https://github.com/delair-ai/disir上找到。
This paper presents an interactive approach for multi-class segmentation of aerial images. Precisely, it is based on a deep neural network which exploits both RGB images and annotations. Starting from an initial output based on the image only, our network then interactively refines this segmentation map using a concatenation of the image and user annotations. Importantly, user annotations modify the inputs of the network - not its weights - enabling a fast and smooth process. Through experiments on two public aerial datasets, we show that user annotations are extremely rewarding: each click corrects roughly 5000 pixels. We analyze the impact of different aspects of our framework such as the representation of the annotations, the volume of training data or the network architecture. Code is available at https://github.com/delair-ai/DISIR.
