This article takes a problem-oriented perspective and presents a comprehensive review of
transfer-learning methods, both shallow and deep, for cross-dataset visual recognition …

Object detection typically assumes that training and test data are drawn from an identical
distribution, which, however, does not always hold in practice. Such a distribution mismatch …

Deep domain adaptation has emerged as a new learning technique to address the lack of
massive amounts of labeled data. Compared to conventional methods, which learn shared …

State-of-the-art object detectors are usually trained on public datasets. They often face
substantial difficulties when applied to a different domain, where the imaging condition …

Background The population of plants is a crucial indicator in plant phenoty** and
agricultural production, such as growth status monitoring, yield estimation, and grain depot …

Most existing unsupervised domain adaptation (UDA) methods are based upon the
assumption that source labeled data come from an identical underlying distribution …

As an alternative to manual pixel-wise annotation, synthetic data has been increasingly
used for training semantic segmentation models. Such synthetic images and semantic labels …

Exploiting synthetic data to learn deep models has attracted increasing attention in recent
years. However, the intrinsic domain difference between synthetic and real images usually …

In order to robustly deploy object detectors across a wide range of scenarios, they should be
adaptable to shifts in the input distribution without the need to constantly annotate new data …

Object detection typically assumes that training and test samples are drawn from an identical
distribution, which, however, does not always hold in practice. Such a distribution mismatch …