Joint training of generic CNN-CRF models with stochastic optimization

Conference item

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 for joint models so far. We show that our learning method is (i) general, i.e. it applies to arbitrary CNN and CRF architectures and potential functions; (ii) scalable, i.e. it has a low memory footprint and straightforwardly parallelizes on GPUs; (iii) easy in implementation. Additionally, the unified CNN-CRF optimization approach simplifies a potential hardware implementation. We empirically evaluate our method on the task of semantic labeling of body parts in depth images and show that it compares favorably to competing techniques.

Authors: Kirillov, A; Schlesinger, D; Zheng, S; Savchynskyy, B; Torr, P

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer, Cham
• Host title: ACCV 2016: Computer Vision – ACCV 2016
• Journal: ACCV 2016: Computer Vision – ACCV 2016
• Volume: 10112
• Pages: 221-236
• Series: Lecture Notes in Computer Science
• Publication date: 2017-03-10
• Acceptance date: 2016-08-19
• DOI: 10.1007/978-3-319-54184-6_14
• ISSN: 0302-9743
• ISBN: 9783319541846