Semantic image segmentation via deep parsing network
Refereed conference paper presented and published in conference proceedings

Times Cited
Altmetrics Information

Other information
AbstractThis paper addresses semantic image segmentation by incorporating rich information into Markov Random Field (MRF), including high-order relations and mixture of label contexts. Unlike previous works that optimized MRFs using iterative algorithm, we solve MRF by proposing a Convolutional Neural Network (CNN), namely Deep Parsing Network (DPN), which enables deterministic end-to-end computation in a single forward pass. Specifically, DPN extends a contemporary CNN architecture to model unary terms and additional layers are carefully devised to approximate the mean field algorithm (MF) for pairwise terms. It has several appealing properties. First, different from the recent works that combined CNN and MRF, where many iterations of MF were required for each training image during back-propagation, DPN is able to achieve high performance by approximating one iteration of MF. Second, DPN represents various types of pairwise terms, making many existing works as its special cases. Third, DPN makes MF easier to be parallelized and speeded up in Graphical Processing Unit (GPU). DPN is thoroughly evaluated on the PASCAL VOC 2012 dataset, where a single DPN model yields a new state-of-the-art segmentation accuracy of 77.5%.
All Author(s) ListLiu Z., Li X., Luo P., Loy C.-C., Tang X.
Name of Conference15th IEEE International Conference on Computer Vision, ICCV 2015
Start Date of Conference11/12/2015
End Date of Conference18/12/2015
Place of ConferenceSantiago
Country/Region of ConferenceRepublic of Chile
Detailed descriptionorganized by IEEE,
Volume Number11-18-December-2015
Pages1377 - 1385
LanguagesEnglish-United Kingdom

Last updated on 2020-13-07 at 00:13