A Practical Transfer Learning Algorithm for Face Verification

Face verification involves determining whether a pair of facial images belongs to the same or different subjects. This problem can prove to be quite challenging in many important applications where labeled training data is scarce, e.g., family album photo organization software. Herein we propose a p...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2013 IEEE International Conference on Computer Vision s. 3208 - 3215
Hlavní autoři: Xudong Cao, Wipf, David, Fang Wen, Genquan Duan, Jian Sun
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.12.2013
Témata:
Algorithm design and analysis
Algorithms
Bayes methods
Bayesian analysis
Computational modeling
Computer programs
Computer vision
Face
face verification
Facial
Joints
Learning
Mathematical models
Software
Testing
transfer learning
Vectors
ISSN:1550-5499
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Face verification involves determining whether a pair of facial images belongs to the same or different subjects. This problem can prove to be quite challenging in many important applications where labeled training data is scarce, e.g., family album photo organization software. Herein we propose a principled transfer learning approach for merging plentiful source-domain data with limited samples from some target domain of interest to create a classifier that ideally performs nearly as well as if rich target-domain data were present. Based upon a surprisingly simple generative Bayesian model, our approach combines a KL-divergence based regularizer/prior with a robust likelihood function leading to a scalable implementation via the EM algorithm. As justification for our design choices, we later use principles from convex analysis to recast our algorithm as an equivalent structured rank minimization problem leading to a number of interesting insights related to solution structure and feature-transform invariance. These insights help to both explain the effectiveness of our algorithm as well as elucidate a wide variety of related Bayesian approaches. Experimental testing with challenging datasets validate the utility of the proposed algorithm.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:1550-5499
DOI:10.1109/ICCV.2013.398