Conditional Random Fields as Recurrent Neural Networks
| Autor: | Philip H. S. Torr, Shuai Zheng, Sadeep Jayasumana, Chang Huang, Dalong Du, Vibhav Vineet, Bernardino Romera-Paredes, Zhizhong Su |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2015 |
| Předmět: |
FOS: Computer and information sciences
Conditional random field Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Deep learning Gaussian Computer Science::Neural and Evolutionary Computation Probabilistic logic ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Computer Science - Computer Vision and Pattern Recognition Machine learning computer.software_genre Convolutional neural network Approximate inference symbols.namesake Recurrent neural network Computer Science::Computer Vision and Pattern Recognition symbols Segmentation Artificial intelligence business computer |
| Popis: | Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To this end, we formulate mean-field approximate inference for the Conditional Random Fields with Gaussian pairwise potentials as Recurrent Neural Networks. This network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a deep network that has desirable properties of both CNNs and CRFs. Importantly, our system 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. We apply the proposed method to the problem of semantic image segmentation, obtaining top results on the challenging Pascal VOC 2012 segmentation benchmark. This paper is published in IEEE ICCV 2015 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|