Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation.
T. Hoang Ngan LeKha Gia QuachKhoa LuuMarios SavvidesChenchen ZhuPublished in: CoRR (2017)
Keyphrases
- recurrent neural networks
- level set
- semantic segmentation
- conditional random fields
- weakly supervised
- active contours
- superpixels
- neural network
- scene classification
- image segmentation
- feed forward
- shape prior
- object categories
- energy function
- artificial neural networks
- object classes
- object class
- image set
- higher order
- machine learning
- long range
- bayesian networks
- three dimensional