Title | ||
---|---|---|
Context-based conditional random fields as recurrent neural networks for image labeling |
Abstract | ||
---|---|---|
This paper proposes new form of convolutional neural network that combines Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRF) based probabilistic graphical modelling, which solve pixel level image labeling problem. In order to reduce the restrictions of deep learning techniques to delineate visual objects,the method fully integrates CRF modelling with CNNs, making it possible to train the whole deep network end-to-end with the usual back-propagation algorithm, avoiding offline post-processing methods for object delineation. Results show that the method is highly accurate and effective. The great result of the experiment have been achieved on the challenging Pascal VOC 2012 segmentation benchmark. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/s11042-019-7564-x | Multimedia Tools and Applications |
Keywords | DocType | Volume |
Image labeling,conditional Radom field, Convolutional neural network,recurrent neural network | Journal | 79 |
Issue | ISSN | Citations |
23 | 1380-7501 | 2 |
PageRank | References | Authors |
0.35 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kun Hu | 1 | 11 | 5.64 |
shuyou zhang | 2 | 38 | 12.57 |
Xinyue Zhao | 3 | 77 | 11.37 |