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...
Huvudupphovsmän: | Kirillov, A, Schlesinger, D, Zheng, S, Savchynskyy, B, Torr, P, Rother, C |
---|---|
Materialtyp: | Conference item |
Publicerad: |
Springer, Cham
2017
|
Liknande verk
Liknande verk
-
Conditional random fields meet deep neural networks for semantic segmentation: combining probabilistic graphical models with deep learning for structured prediction
av: Arnab, A, et al.
Publicerad: (2018) -
Study on MRI Medical Image Segmentation Technology Based on CNN-CRF Model
av: Naiqin Feng, et al.
Publicerad: (2020-01-01) -
Efficient continuous relaxations for dense CRF
av: Bunel, R, et al.
Publicerad: (2016) -
A projected gradient descent method for CRF inference allowing end-to-end training of arbitrary pairwise potentials
av: Larsson, M, et al.
Publicerad: (2018) -
Semantic Segmentation of Remote Sensing Imagery Based on Multiscale Deformable CNN and DenseCRF
av: Xiang Cheng, et al.
Publicerad: (2023-02-01)