语义分割-- SegNet：A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
2017-05-26 14:25
761 查看
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
PAMI 2017
http://mi.eng.cam.ac.uk/projects/segnet/
下载下面两个代码合到一起
https://github.com/alexgkendall/SegNet-Tutorial
https://github.com/alexgkendall/caffe-segnet
SegNet has an encoder network and a corresponding decoder network, followed by a final pixelwise classification layer.
SegNet 有三个部分构成：一个 encoder network，一个对应的 decoder network，最后一个像素级别的分类层
本文最大的亮点在： 在 encoder 阶段我们做 max-pooling时，我们将 pooling indices 记录下来，在decoder upsamples 使用这些 pooling indices 得到稀疏的 upsampled maps，再用 trainable filters 进行卷积得到 dense feature maps。
和 DeconvNet 类似。
系统结构示意图：
SegNet 和 FCN decoder 方式对比
看分割算法，主要看人家是怎么做 decoder low resolution feature map 即怎么放大特征图
PAMI 2017
http://mi.eng.cam.ac.uk/projects/segnet/
下载下面两个代码合到一起
https://github.com/alexgkendall/SegNet-Tutorial
https://github.com/alexgkendall/caffe-segnet
SegNet has an encoder network and a corresponding decoder network, followed by a final pixelwise classification layer.
SegNet 有三个部分构成：一个 encoder network，一个对应的 decoder network，最后一个像素级别的分类层
本文最大的亮点在： 在 encoder 阶段我们做 max-pooling时，我们将 pooling indices 记录下来，在decoder upsamples 使用这些 pooling indices 得到稀疏的 upsampled maps，再用 trainable filters 进行卷积得到 dense feature maps。
和 DeconvNet 类似。
系统结构示意图：
SegNet 和 FCN decoder 方式对比
看分割算法，主要看人家是怎么做 decoder low resolution feature map 即怎么放大特征图
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation 视频语义分割demo跑通
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation 论文阅读
- 论文笔记 | SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
- [论文笔记]SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
- 【SegNet】SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image
- TPAMI2017 SegNet：A Deep Convolutional Encoder-Decoder Architecture for Scene Segmentation
- SegNet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling
- 【论文翻译】SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
- 医学图像分割--U-Net: Convolutional Networks for Biomedical Image Segmentation
- 语义分割DeepLab v2--DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolut
- 语义分割--Deep Dual Learning for Semantic Image Segmentation
- 语义分割--LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation
- DeepLab：深度卷积网络，多孔卷积 和全连接条件随机场 的图像语义分割 Semantic Image Segmentation with Deep Convolutional Nets, Atro
- 医学图像分割--U-Net: Convolutional Networks for Biomedical Image Segmentation
- 语义分割--Learning Object Interactions and Descriptions for Semantic Image Segmentation
- 语义分割--Fully Convolutional DenseNets for Semantic Segmentation
- 用于语义分割的全卷积网络 （fully convolutional networks for semantic segmentation）
- 【图像语义分割】Fully Convolutional Networks for Semantic Segmentation
- 语义分割--Efficient Deep Models for Monocular Road Segmentation