没有合适的资源?快使用搜索试试~ 我知道了~
首页Deep lab家族ppt.pdf
资源详情
资源评论
资源推荐

Rethinking Atrous
Convolution for
Semantic Image
Segmentation
LIANG-CHIEH CHEN, GEORGE PAPANDREOU, FLORIAN
SCHROFF, HARTWIG ADAM
Sivan Doveh
Jenny Zukerman
Deep learning seminar 2017/18

Agenda
Semantic segmentation
Main idea of DeepLab
DeepLabV1
DeepLabV2
DeepLabV3

Semantic Segmentation
Semantic Segmentation
Semantic segmentation is understanding an image at pixel level i.e, we want
to assign each pixel in the image an object class
Partitioning an image into regions of meaningful objects.
Assign an object category label.

Semantic Segmentation
Why semantic segmentation?
Autonomous driving
Medical purposes
We will focus on 3 papers:
DeepLabV1
DeepLabV2
DeepLabV3

DeepLabV1 & DeepLabV2
Use DCNN for classification to generate a rough prediction of segmentation
(smooth, blurry heat map)
Refine prediction with conditional random field (CRF)
剩余25页未读,继续阅读

















安全验证
文档复制为VIP权益,开通VIP直接复制

评论0