Day-18 Computer Vision Learning DeconvNet Unpooling Layer (Semantic Segmentation) 🔸 Originally, it was submitted to 2015 ICCV with more than 3079 citations. 🔸 The deconvolution network (DeconvNet) is composed of deconvolution and unpooling layers. 🔸 First Author Hyeonwoo Noh is working for OpenAI ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://bit.ly/3qyNV5p Tensorflow : https://bit.ly/3nOmtis Caffe : https://lnkd.in/e-pSxwY Pytorch : https://lnkd.in/eZvrpr9 Keras : https://lnkd.in/ep_6kQU ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 DConvNet Use VGG as backbone. 🔸 First part is Fully Convolution Network and Second part is Deconvolution Network. #innovation #artificialintelligence #computervision
Sign in to view more content
Create your free account or sign in to continue your search
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
it uses VGGNet as the backbone. The first part is a convolution network which is as usual as FCN, with conv and pooling layers. The second part is the deconvolution network which is a novel part in this paper.