Fast and Differentiable Message Passing on Pairwise Markov Random Fields
Zhiwei Xu (Australian National University)*, Thalaiyasingam Ajanthan (ANU), RICHARD HARTLEY (Australian National University, Australia)
Keywords: Optimization Methods
Abstract:
Despite the availability of many Markov Random Field (MRF) optimization algorithms, their widespread usage is currently limited due to imperfect MRF modelling arising from hand-crafted model parameters and the selection of inferior inference algorithm. In addition to differentiability, the two main aspects that enable learning these model parameters are the forward and backward propagation time of the MRF optimization algorithm and its inference capabilities. In this work, we introduce two fast and differentiable message passing algorithms, namely, Iterative Semi-Global Matching Revised (ISGMR) and Parallel Tree-Reweighted Message Passing (TRWP) which are greatly sped up on a GPU by exploiting massive parallelism. Specifically, ISGMR is an iterative and revised version of the standard SGM for general pairwise MRFs with improved optimization effectiveness, and TRWP is a highly parallel version of Sequential TRW (TRWS) for faster optimization. Our experiments on the standard stereo and denoising benchmarks demonstrated that ISGMR and TRWP achieve much lower energies than SGM and Mean-Field (MF), and TRWP is two orders of magnitude faster than TRWS without losing effectiveness in optimization. We further demonstrated the effectiveness of our algorithms on end-to-end learning for semantic segmentation. Notably, our CUDA implementations are at least 7 and 700 times faster than PyTorch GPU implementations for forward and backward propagation respectively, enabling efficient end-to-end learning with message passing.
SlidesLive
Similar Papers
Progressive Batching for Efficient Non-linear Least Squares
Huu Le (Chalmers University of Technology)*, Christopher Zach (Chalmers University), Edward Rosten (Snap Inc.), Oliver J. Woodford (Snap Inc)

CS-MCNet:A Video Compressive Sensing Reconstruction Network with Interpretable Motion Compensation
Bowen Huang (Fudan University)*, Jinjia Zhou (Hosei University), Xiao Yan (Fudan University), Ming'e Jing (Fudan University), Rentao Wan (Fudan University), Yibo Fan (Fudan University)

Lossless Image Compression Using a Multi-Scale Progressive Statistical Model
Honglei Zhang (Nokia Technologies)*, Francesco Cricri (Nokia Technologies), Hamed R. Tavakoli (Nokia Technologies), Nannan Zou (Tampere University), Emre Aksu (Nokia Technologies), Miska M. Hannuksela (Nokia Technologies)
