Transfer Learning for Visual Categorization: A Survey

Ling Shao, Fan Zhu, Xuelong Li

Research output: Contribution to journalArticlepeer-review

501 Citations (Scopus)


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 crossdomain 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.
Original languageEnglish
Pages (from-to)1019-1034
JournalIEEE Transactions on Neural Networks and Learning Systems
Issue number5
Publication statusPublished - May 2015


Dive into the research topics of 'Transfer Learning for Visual Categorization: A Survey'. Together they form a unique fingerprint.

Cite this