cv-segNet学习笔记
显著特点
segNet的特点最显著特点就是decoder网络复用了对应的encoder网络的降采样层来升采样(即max-pooling indices)
文章结构
section2 最近成就
section3 segNet及分析
seciton4 评价segNet表现
section5 未来工作
section6 结论
section2
before deep network: hand engineering features + classifier
CamVid
- SfM+Random Forest/Boosting
- CRF
Indoor NYUdataset
- RGB-SIFT/depth-SIFT/piexel location/LBP
- resl-time joint reconstruction and semantic segmentation RandomForest
deep CNN
- 复制分类特征用于分割replicating the deepest layer features in blocks to match image
- merge rnn 低分辨率
- encoder+decoder network
- CRF-RNN
- 多规格深度结构:a.使用少量规模和对应featuremap;b,结合不同层的featuremap
section3
- encoder + 对应的decoder
I'm a fucKing fake coder!