Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials

DOI10.1137/18M1178104zbMath1423.90263arXiv1805.09028OpenAlexW2963979276WikidataQ128454013 ScholiaQ128454013MaRDI QIDQ5236643

Thalaiyasingam Ajanthan, M. Pawan Kumar, Rudy Bunel, Mathieu Salzmann, Philip H. S. Torr, Thomas Joy, Alban Desmaison, Pushmeet Kohli

Publication date: 9 October 2019

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1805.09028

zbMATH Keywords

optimizationenergy minimizationsemantic segmentationCRFsMRFs

Mathematics Subject Classification ID

Programming involving graphs or networks (90C35)

Related Items (2)

Revisiting Deep Structured Models for Pixel-Level Labeling with Gradient-Based Inference ⋮ Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials

Uses Software

• DeepLab
• Spearmint
• PASCAL VOC

Cites Work

• Inference methods for CRFs with co-occurrence statistics
• Filter-based mean-field inference for random fields with higher-order terms and product label-spaces
• Duality Between Subgradient and Conditional Gradient Methods
• Approximation algorithms for classification problems with pairwise relationships
• Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials