Optimization of robust loss functions for weakly-labeled image taxonomies

DOI10.1007/S11263-012-0561-4MaRDI QIDQ2254258zbMATH OpenOpenAlexFDO

Authors Julian J. McAuley, Arnau Ramisa, Tibério S. Caetano

Publication date 4 February 2015

Published in International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11263-012-0561-4

zbMATH Keywords

image labelingimage taggingimage taxonomiesstructured learning

Mathematics Subject Classification ID

Information storage and retrieval of data (68P20) Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Machine vision and scene understanding (68T45)

Recommendations

• Learning safe multi-label prediction for weakly labeled data
• Convex and scalable weakly labeled SVMs
• Learning from partial labels
• Continuous multiclass labeling approaches and algorithms
• Robust supervised classification with mixture models: learning from data with uncertain labels

Cites work

• Hash kernels for structured data
• Large margin methods for structured and interdependent output variables
• Optimization of robust loss functions for weakly-labeled image taxonomies
• The Concave-Convex Procedure

Cited in

(3)

• Learning safe multi-label prediction for weakly labeled data
• Instance weighting through data imprecisiation
• Optimization of robust loss functions for weakly-labeled image taxonomies

Describes a project that uses

Uses Software

• Caltech-256
• TagProp
• WordNet
• ImageNet
• PASCAL VOC

This page was built for publication: Optimization of robust loss functions for weakly-labeled image taxonomies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2254258)