ilydouble
commented
6 years ago 11 https://dl.acm.org/citation.cfm?id=3106963 这篇文章是针对医学图像标注数据少的问题提出堆叠全卷积神经网络的方法 12 https://cs224d.stanford.edu/reports/Lambert.pdf 是斯坦福大学的研究报告，用Stacked RNN处理图像语义分割，就是2层RNN，据说效果比传统的方法好，网速太慢看了前两页
1 Automatic Pixelwise Object Labeling for Aerial Imagery Using Stacked U-Nets https://arxiv.org/abs/1803.04953 类似于SDN的思想，就是把多个U-NET堆叠在一起，解决遥感图像的标注，没有说明为什么堆叠就带来了好的效果
2 Creating Roadmaps in Aerial Images with Generative Adversarial Networks and Smoothing-based Optimization http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w30/Costea_Creating_Roadmaps_in_ICCV_2017_paper.pdf 很有意思的用GAN进行分割的文章，主要是提出一个DHGAN，这不是一个新的GAN结构，而是把两个GAN连接在一起，第一个解决道路提取，第二个解决关键节点提取的问题。
3 Joint learning from Earth Observation and OpenStreetMap data to get faster better semantic maps http://openaccess.thecvf.com/content_cvpr_2017_workshops/w18/papers/Audebert_Joint_Learning_From_CVPR_2017_paper.pdf
4 SEMANTIC SEGMENTATION OF AERIAL IMAGES WITH EXPLICIT CLASS-BOUNDARY MODELING http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8128165 这篇文章在ISPRS的V城市数据上做的分割实验，它的实验非常复杂，包含两个部分：第一个部分是HED提取边缘，第二个部分是HED和图像一起输入网络，在第二部分用三种网络VGG，SEGNET，FCN结构集成，最后还修改了数据中的错误，得到了比较大的分割精度的提升。发表在IGARSS2017的会议上。
5 Classification with an edge: Improving semantic image segmentation with boundary detection We present an end-to-end trainable deep convolutional neural network (DCNN) for semantic segmentation with built-in awareness of semantically meaningful boundaries. Semantic segmentation is a fundamental remote sensing task, and most state-of-the-art methods rely on DCNNs as their workhorse. A major reason for their success is that deep networks learn to accumulate contextual information over very large receptive fields. However, this success comes at a cost, since the associated loss of effective spatial resolution washes out high-frequency details and leads to blurry object boundaries. Here, we propose to counter this effect by combining semantic segmentation with semantically informed edge detection, thus making class boundaries explicit in the model. First, we construct a comparatively simple, memory-efficient model by adding boundary detection to the segnet encoder-decoder architecture. Second, we also include boundary detection in fcn-type models and set up a high-end classifier ensemble. We show that boundary detection significantly improves semantic segmentation with CNNs in an end-to-end training scheme. Our best model achieves >90% overall accuracy on the ISPRS Vaihingen benchmark. 上面的ABSTRACT表明这篇文章跟上一篇文章基本思路一样，但是这个文章扩充到15也，发表在ISPRS的期刊上，影响因子6左右
6 Fast Residual Forests: Rapid Ensemble Learning for Semantic Segmentation http://proceedings.mlr.press/v78/zuo17a/zuo17a.pdf
7 Virtual-to-Real: Learning to Control in Visual Semantic Segmentation https://arxiv.org/pdf/1802.00285.pdf 这是一篇指的深入阅读的文章，遗憾的是，我并没有花时间深入，该工作包含对抗网络，包含增强学习，提出了虚拟到真实融合来解决分割问题的一种框架方法。牛！
8 Semantic segmentation of vegetation images acquired by unmanned aerial vehicles using an ensemble of ConvNets
9 Semantic labeling of high-resolution aerial images using an ensemble of fully convolutional networks
10 Exploring Context with Deep Structured models for Semantic Segmentation https://arxiv.org/pdf/1603.03183.pdf