Optimizing the relevance-redundancy tradeoff for efficient semantic segmentation

DOI10.1007/978-3-319-18461-6_20MaRDI QIDQ3300304zbMATH OpenOpenAlexFDO

Authors Caner Hazırbaş, Julia Diebold, Daniel Cremers

Publication date 28 July 2020

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-319-18461-6_20

zbMATH Keywords

feature analysisfeature selectionimage segmentationsemantic scene understanding

Mathematics Subject Classification ID

Machine vision and scene understanding (68T45) Computing methodologies for image processing (68U10)

Recommendations

• Subset selection for visualization of relevant image fractions for deep learning based semantic image segmentation
• Efficient feature selection via analysis of relevance and redundancy
• Efficient feature selection using shrinkage estimators
• Optimizing training set construction for video semantic classification
• Evaluating and selecting features via information theoretic lower bounds of feature inner correlations for high-dimensional data

Cites work

• A Convex Approach to Minimal Partitions
• Inference methods for CRFs with co-occurrence statistics

Cited in

(3)

• Subset selection for visualization of relevant image fractions for deep learning based semantic image segmentation
• OCNet: object context for semantic segmentation
• Semantic identification: balancing between complexity and validity

Describes a project that uses

Uses Software

• NYU Depth

This page was built for publication: Optimizing the relevance-redundancy tradeoff for efficient semantic segmentation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3300304)