Abstract | ||
---|---|---|
Current practice in convolutional neural networks (CNN) remains largely bottom-up and the role of top-down process in CNN for pattern analysis and visual inference is not very clear. In this paper, we propose a new method for structured labeling by developing convolutional pseudoprior (ConvPP) on the ground-truth labels. Our method has several interesting properties: (1) compared with classic machine learning algorithms like CRFs and Structural SVM, ConvPP automatically learns rich convolutional kernels to capture both short-and long-range contexts; (2) compared with cascade classifiers like Auto-Context, ConvPP avoids the iterative steps of learning a series of discriminative classifiers and automatically learns contextual configurations; (3) compared with recent efforts combining CNN models with CRFs and RNNs, ConvPP learns convolution in the labeling space with improved modeling capability and less manual specification; (4) compared with Bayesian models like MRFs, ConvPP capitalizes on the rich representation power of convolution by automatically learning priors built on convolutional filters. We accomplish our task using pseudo-likelihood approximation to the prior under a novel fixed-point network structure that facilitates an end-to-end learning process. We show state-of-the-art results on sequential labeling and image labeling benchmarks. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-46493-0_19 | COMPUTER VISION - ECCV 2016, PT IV |
Keywords | Field | DocType |
Structured prediction, Deep learning, Semantic segmentation, Top-down processing | Pattern recognition,Inference,Computer science,Convolution,Convolutional neural network,Support vector machine,Artificial intelligence,Prior probability,Discriminative model,CRFS,Machine learning,Bayesian probability | Conference |
Volume | ISSN | Citations |
9908 | 0302-9743 | 3 |
PageRank | References | Authors |
0.38 | 10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Saining Xie | 1 | 231 | 12.45 |
Xun Huang | 2 | 116 | 5.29 |
Zhuowen Tu | 3 | 3663 | 215.79 |