DeepAI AI Chat
Log In Sign Up

Local Perturb-and-MAP for Structured Prediction

by   Gedas Bertasius, et al.

Conditional random fields (CRFs) provide a powerful tool for structured prediction, but cast significant challenges in both the learning and inference steps. Approximation techniques are widely used in both steps, which should be considered jointly to guarantee good performance (a.k.a. "inferning"). Perturb-and-MAP models provide a promising alternative to CRFs, but require global combinatorial optimization and hence they are usable only on specific models. In this work, we present a new Local Perturb-and-MAP (locPMAP) framework that replaces the global optimization with a local optimization by exploiting our observed connection between locPMAP and the pseudolikelihood of the original CRF model. We test our approach on three different vision tasks and show that our method achieves consistently improved performance over other approximate inference techniques optimized to a pseudolikelihood objective. Additionally, we demonstrate that we can integrate our method in the fully convolutional network framework to increase our model's complexity. Finally, our observed connection between locPMAP and the pseudolikelihood leads to a novel perspective for understanding and using pseudolikelihood.


page 6

page 8


Hinge-loss Markov Random Fields: Convex Inference for Structured Prediction

Graphical models for structured domains are powerful tools, but the comp...

Discriminative Training of Deep Fully-connected Continuous CRF with Task-specific Loss

Recent works on deep conditional random fields (CRF) have set new record...

Unravelling the Architecture of Membrane Proteins with Conditional Random Fields

In this paper, we will show that the recently introduced graphical model...

Geometric Matrix Completion with Deep Conditional Random Fields

The problem of completing high-dimensional matrices from a limited set o...

Fast as CHITA: Neural Network Pruning with Combinatorial Optimization

The sheer size of modern neural networks makes model serving a serious c...

Graph cuts always find a global optimum (with a catch)

We prove that the alpha-expansion algorithm for MAP inference always ret...

Structured Convolutional Kernel Networks for Airline Crew Scheduling

Motivated by the needs from an airline crew scheduling application, we i...