Joint training of generic CNN-CRF models with stochastic optimization
We propose a new CNN-CRF end-to-end learning framework, which is based on joint stochastic optimization with respect to both Convolutional Neural Network (CNN) and Conditional Random Field (CRF) parameters. While stochastic gradient descent is a standard technique for CNN training, it was not used f...
Автори: | Kirillov, A, Schlesinger, D, Zheng, S, Savchynskyy, B, Torr, P, Rother, C |
---|---|
Формат: | Conference item |
Опубліковано: |
Springer, Cham
2017
|
Схожі ресурси
-
Conditional random fields meet deep neural networks for semantic segmentation: combining probabilistic graphical models with deep learning for structured prediction
за авторством: Arnab, A, та інші
Опубліковано: (2018) -
Study on MRI Medical Image Segmentation Technology Based on CNN-CRF Model
за авторством: Naiqin Feng, та інші
Опубліковано: (2020-01-01) -
Efficient continuous relaxations for dense CRF
за авторством: Bunel, R, та інші
Опубліковано: (2016) -
A projected gradient descent method for CRF inference allowing end-to-end training of arbitrary pairwise potentials
за авторством: Larsson, M, та інші
Опубліковано: (2018) -
Semantic Segmentation of Remote Sensing Imagery Based on Multiscale Deformable CNN and DenseCRF
за авторством: Xiang Cheng, та інші
Опубліковано: (2023-02-01)