Transfer Learning for Visual Categorization: A Survey

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…

• NN
  National Natural Science Foundation of China

  Awards: 61072093, 61125106
• NK
  National Key Research and Development Program of China

  Award: 2012CB316400