Revisiting Deep Structured Models for Pixel-Level Labeling with Gradient-Based Inference

DOI10.1137/18M1167267MaRDI QIDQ5230425zbMATH OpenOpenAlexWikidataFDO

Authors Måns Larsson, Anurag Arnab, Shuai Zheng, Philip H. S. Torr, Fredrik Kahl

Publication date 22 August 2019

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

Full work available at URL https://doi.org/10.1137/18m1167267

zbMATH Keywords

deep learningconditional random fieldssemantic segmentationdeep structured models

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10) Machine vision and scene understanding (68T45)

Recommendations

• A regularized convolutional neural network for semantic image segmentation
• Conditional random fields for image labeling

Cites work

• scientific article; zbMATH DE number 2062547 (Why is no real title available?)
• Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials
• Filter-based mean-field inference for random fields with higher-order terms and product label-spaces
• Markov random fields for vision and image processing
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Probabilistic graphical models.
• Pseudo-Boolean optimization

Cited in

(4)

• Harmony potentials fusing global and local scale for semantic image segmentation
• Distribution-aware margin calibration for semantic segmentation in images
• Weakly-supervised semantic segmentation by iterative affinity learning
• Subset selection for visualization of relevant image fractions for deep learning based semantic image segmentation

Describes a project that uses

Uses Software

• Faster R-CNN
• RefineNet
• PASCAL VOC
• MS-COCO
• Caffe
• GrabCut
• DeepLab

This page was built for publication: Revisiting Deep Structured Models for Pixel-Level Labeling with Gradient-Based Inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5230425)