Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling
Authors:
- Andrew KaeAKAndrew Kae
- Kihyuk SohnKSKihyuk Sohn
- Honglak LeeHLHonglak Lee
- Erik Learned-MillerELErik Learned-Miller
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 2019-2026
Abstract
Conditional random fields (CRFs) provide powerful tools for building models to label image segments. They are particularly well-suited to modeling local interactions among adjacent regions (e.g., super pixels). However, CRFs are limited in dealing with complex, global (long-range) interactions between regions. Complementary to this, restricted Boltzmann machines (RBMs) can be used to model global shapes produced by segmentation models. In this work, we present a new model that uses the combined power of these two network types to build a state-of-the-art labeler. Although the CRF is a good baseline labeler, we show how an RBM can be added to the architecture to provide a global shape bias that complements the local modeling provided by the CRF. We demonstrate its labeling performance for the parts of complex face images from the Labeled Faces in the Wild data set. This hybrid model produces results that are both quantitatively and qualitatively better than the CRF alone. In addition to high-quality labeling results, we demonstrate that the hidden units in the RBM portion of our model can be interpreted as face attributes that have been learned without any attribute-level supervision.Keywords
This publication has 17 references indexed in Scilit:
- The Shape Boltzmann Machine: A strong model of object shape2012
- Learning hierarchical representations for face verification with convolutional deep belief networks2012
- Attribute Discovery via Predictable Discriminative Binary Codes2012
- A Compositional Exemplar-Based Model for Hair Segmentation2011
- Effective Unconstrained Face Recognition by Combining Multiple Descriptors and Learned Background StatisticsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Towards unconstrained face recognition2008
- Detection and analysis of hairIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Combining Top-Down and Bottom-Up Segmentation2005
- Learning to detect natural image boundaries using local brightness, color, and texture cuesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002