READING NOTE: Semantic Object Parsing with Graph LSTM

原创 2016年05月30日 20:34:59

TITLE: Semantic Object Parsing with Graph LSTM

AUTHER: Xiaodan Liang, Xiaohui Shen, Jiashi Feng, Liang Lin, Shuicheng Yan

ASSOCIATION: National University of Singapore, Sun Yat-sen University, Adobe Research

FROM: arXiv:1603.07063

CONTRIBUTIONS

  1. A novel Graph LSTM structure is proposed handle general graph-structured data, which effectively exploits global context by superpixels extracted by over-segmentation.
  2. A confidence-driven scheme is proposed to select the starting node and the order of updating sequences.
  3. In each Graph LSTM unit, different forget gates for the neighboring nodes are learned to dynamically incorporate the local contextual interactions in accordance with their semantic relations.

METHOD

The main steps of the method is shown in the following figure.

  1. The input image first passes through a stack of convolutional layers to generate the convolutional feature maps.
  2. The convolutional feature maps are further used to generate an initial semantic confidence map for each pixel.
  3. The input image is over-segmented to multiple superpixels. For each superpixel, a feature vector is extracted from the upsampled convolutional feature maps.
  4. The first Graph LSTM takes the feature vector of every superpixel as input to compute a better state.
  5. The second Graph LSTM takes the feature vector of every superpixel and the output of first Graph LSTM as input.
  6. The update sequence of the superpixel is according to the initial confidence of the superpiexels.
  7. several 1×1 convolution filters are employed to produce the final parsing results.

some details

A graph structure is built based on the superpixels. The nodes are the superpixels and the nodes are linked when they are adjacent. The history information used by the G-LSTM for one superpixel come from the adjacent superpixels.

ADVANTAGES

  1. Constructed on superpixels generated by oversegmentation, the Graph LSTM is more naturally aligned with the visual patterns in the image.
  2. Adaptively learning the forget gates with respect to different neighboring nodes when updating the hidden states of a certain node is beneficial to model various neighbor connections.
版权声明:本文为博主原创文章,未经博主允许不得转载。欢迎访问博主个人主页 http://joshua881228.webfactional.com/ 举报

相关文章推荐

READING NOTE: Object Detection by Labeling Superpixels

READING NOTE: Object Detection by Labeling Superpixels

「MICCAI 2016」Reading Note

Sina Weibo:东莞小锋子Sexyphone Tencent E-mail:403568338@qq.com     此文记录MICCAI 2016会议论文阅读笔记,主要通过论文题目和...

精选:深入理解 Docker 内部原理及网络配置

网络绝对是任何系统的核心,对于容器而言也是如此。Docker 作为目前最火的轻量级容器技术,有很多令人称道的功能,如 Docker 的镜像管理。然而,Docker的网络一直以来都比较薄弱,所以我们有必要深入了解Docker的网络知识,以满足更高的网络需求。

Latent semantic analysis note(LSA)

1 LSA Introduction LSA(latent semantic analysis)潜在语义分析,也被称为LSI(latent semantic index),是Scott ...

Latent semantic analysis note(LSA)

1 LSA Introduction LSA(latent semantic analysis)潜在语义分析,也被称为LSI(latent semantic index),是Scott ...

Latent semantic analysis note(LSA)

1 LSA Introduction LSA(latent semantic analysis)潜在语义分析,也被称为LSI(latent semantic index),是Scott Deer...

Parsing Arguments with getopt

getopt used for parse arguments passed to main(int argc, char**argv) function under cmdline environm...
  • flxue
  • flxue
  • 2015-03-11 20:51
  • 483

Parsing JSON With SBJSON

转自: http://jasarien.com/?p=428 So the previous post focussed on retrieving data from a ...

Latent semantic analysis note(LSA) or Latent Semantic Indexing (LSI)

1 LSA Introduction LSA(latent semantic analysis)潜在语义分析,也被称为LSI(latent semantic index),是Scott Deer...
  • vfgbv
  • vfgbv
  • 2014-11-10 11:21
  • 312

My note for reading English reference

Core Java Volume II-Advanced Features for    , please contact: visit us on the web: oracle ...

Parsing XML Files with PowerShell

In the context of using Windows PowerShell for lightweight software test automation, one of the most...
返回顶部
收藏助手
不良信息举报
您举报文章:深度学习:神经网络中的前向传播和反向传播算法推导
举报原因:
原因补充:

(最多只允许输入30个字)