Transfer Learning for Visual Categorization: A Survey
Top Cited Papers
- 1 July 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 26 (5), 1019-1034
- https://doi.org/10.1109/tnnls.2014.2330900
Abstract
Regular machine learning and data mining techniques study the training data for future inferences under a major assumption that the future data are within the same feature space or have the same distribution as the training data. However, due to the limited availability of human labeled training data, training data that stay in the same feature space or have the same distribution as the future data cannot be guaranteed to be sufficient enough to avoid the over-fitting problem. In real-world applications, apart from data in the target domain, related data in a different domain can also be included to expand the availability of our prior knowledge about the target future data. Transfer learning addresses such cross-domain learning problems by extracting useful information from data in a related domain and transferring them for being used in target tasks. In recent years, with transfer learning being applied to visual categorization, some typical problems, e.g., view divergence in action recognition tasks and concept drifting in image classification tasks, can be efficiently solved. In this paper, we survey state-of-the-art transfer learning algorithms in visual categorization applications, such as object recognition, image classification, and human action recognition.Keywords
Funding Information
- National Basic Research Program of China (973 Program) (2012CB316400)
- University of Sheffield, Sheffield, U.K.
- National Natural Science Foundation of China (61125106, 61072093)
This publication has 75 references indexed in Scilit:
- Multi-view action recognition using local similarity random forests and sensor fusionPattern Recognition Letters, 2013
- Transfer latent variable model based on divergence analysisPattern Recognition, 2011
- Learning author-topic models from text corporaACM Transactions on Information Systems, 2010
- Free viewpoint action recognition using motion history volumesComputer Vision and Image Understanding, 2006
- Integrating structured biological data by Kernel Maximum Mean DiscrepancyBioinformatics, 2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Task-specific gesture analysis in real-time using interpolated viewsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Principal component analysisChemometrics and Intelligent Laboratory Systems, 1987
- Recognition-by-components: A theory of human image understanding.Psychological Review, 1987