Zero-shot Domain Adaptation Based on Attribute Information

In many algorithms for supervised learning, it is assumed that training data are obtained from the same distribution as that of test data [1]. Unfortunately, this assumption is often violated in practical applications. For example, Figure 1 shows images of two different surveillance videos that are obtained from Video Surveillance Online Repository [2]. Suppose we want to recognize vehicles from these videos. Since the position and pose of the camera are different, the appearance of the vehicle is somewhat different between two videos. Due to this difference, even if we train a highly accurate classifier on video A, it may work poorly on video B. Such discrepancy has recently become a major problem in pattern recognition, because it is often difficult to obtain training data that are sufficiently similar to the test data. To deal with this problem, domain adaptation techniques have been proposed.