Learning kernels for unsupervised domain adaptation with applications to visual object recognition

DOI10.1007/S11263-014-0718-4zbMATH Open1328.68240OpenAlexW2004273576MaRDI QIDQ903526FDOQ903526

Authors: Boqing Gong, Kristen Grauman, Fei Sha 

Publication date: 6 January 2016

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

Full work available at URL: https://doi.org/10.1007/s11263-014-0718-4

Recommendations

• Asymmetric and category invariant feature transformations for domain adaptation
• Distribution-matching embedding for visual domain adaptation
• Finding robust transfer features for unsupervised domain adaptation
• A kernel learning framework for domain adaptation learning
• A theory of learning from different domains

zbMATH Keywords

kernelsobject recognitiondomain adaptationcross-dataset bias

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Machine vision and scene understanding (68T45)

Cites Work

• A kernel two-sample test
• Improving predictive inference under covariate shift by weighting the log-likelihood function
• Learning the kernel matrix with semidefinite programming
• Title not available (Why is that?)
• A theory of learning from different domains
• Title not available (Why is that?)

Cited In (17)

• Spectral domain-transfer learning
• An Embarrassingly Simple Approach to Visual Domain Adaptation
• Unsupervised domain adaptation in the wild via disentangling representation learning
• Domain-adversarial training of neural networks
• Robust unsupervised domain adaptation for neural networks via moment alignment
• Learning smooth representations with generalized softmax for unsupervised domain adaptation
• Asymmetric and category invariant feature transformations for domain adaptation
• Domain adaptation for face recognition: targetize source domain bridged by common subspace
• Domain adaptation for structured regression
• Model-driven domain adaptation on product manifolds for unconstrained face recognition
• Distribution-matching embedding for visual domain adaptation
• Weakly-supervised cross-domain dictionary learning for visual recognition
• Robust multi-source adaptation visual classification using supervised low-rank representation
• A kernel learning framework for domain adaptation learning
• Robust adaptation regularization based on within-class scatter for domain adaptation
• Multi-source adaptation joint kernel sparse representation for visual classification
• Video domain adaptation based on optimal transport in Grassmann manifolds

Uses Software

• ImageNet
• SURF
• Caltech-256
• PASCAL VOC
• LabelMe

This page was built for publication: Learning kernels for unsupervised domain adaptation with applications to visual object recognition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q903526)