Timezone: »

Proximal Deep Structured Models
Shenlong Wang · Sanja Fidler · Raquel Urtasun

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #80

Many problems in real-world applications involve predicting continuous-valued random variables that are statistically related. In this paper, we propose a powerful deep structured model that is able to learn complex non-linear functions which encode the dependencies between continuous output variables. We show that inference in our model using proximal methods can be efficiently solved as a feed-foward pass of a special type of deep recurrent neural network. We demonstrate the effectiveness of our approach in the tasks of image denoising, depth refinement and optical flow estimation.

Author Information

Shenlong Wang (University of Toronto)
Sanja Fidler (University of Toronto)
Raquel Urtasun (University of Toronto)

More from the Same Authors