Timezone: »

 
Poster
Deeply Learning the Messages in Message Passing Inference
Guosheng Lin · Chunhua Shen · Ian Reid · Anton van den Hengel

Tue Dec 08 04:00 PM -- 08:59 PM (PST) @ 210 C #22 #None
in Poster Session »

Deep structured output learning shows great promise in tasks like semantic image segmentation. We proffer a new, efficient deep structured model learning scheme, in which we show how deep Convolutional Neural Networks (CNNs) can be used to directly estimate the messages in message passing inference for structured prediction with Conditional Random Fields CRFs). With such CNN message estimators, we obviate the need to learn or evaluate potential functions for message calculation. This confers significant efficiency for learning, since otherwise when performing structured learning for a CRF with CNN potentials it is necessary to undertake expensive inference for every stochastic gradient iteration. The network output dimension of message estimators is the same as the number of classes, rather than exponentially growing in the order of the potentials. Hence it is more scalable for cases that a large number of classes are involved. We apply our method to semantic image segmentation and achieve impressive performance, which demonstrates the effectiveness and usefulness of our CNN message learning method.

Author Information

Guosheng Lin (The University of Adelaide)
Chunhua Shen (University of Adelaide)
Ian Reid (University of Adelaide)
Anton van den Hengel (University of Adelaide)

More from the Same Authors