Deeply Learning the Messages in Message Passing Inference

TL;DR

This paper introduces a novel deep learning approach that uses CNNs to estimate messages in message passing inference for structured prediction, significantly improving efficiency and scalability in tasks like semantic image segmentation.

Contribution

It proposes a new CNN-based message estimation scheme that eliminates the need for potential function learning, enhancing efficiency and scalability in structured prediction models.

Findings

Achieved 73.4% intersection-over-union on PASCAL VOC 2012 test set.

Outperformed previous methods using only VOC training images.

Demonstrated effectiveness of CNN message learning in structured prediction.

Abstract

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 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 for message estimation is the same as the number of classes, in contrast to the network output for general CNN potential functions in CRFs, which is exponential in the order of the potentials. Hence CNN message learning has fewer network parameters and is more scalable for cases that a large number of classes are involved. We apply our method to semantic image segmentation on the PASCAL VOC 2012 dataset. We achieve an intersection-over-union score of 73.4 on its test set, which is the best reported result for methods using the VOC training images alone. This impressive performance demonstrates the effectiveness and usefulness of our CNN message learning method.