Summer School on Advances in Image, Motion and Video Coding and Processing

Location and Date:TBA

The main theme of this Summer School is the theoretical, algorithmic, and empirical analysis of machine learning techniques when here is a mismatch between the training and the test distributions. This includes the crucial scenario of domain adaptation where the training examples are drawn from a source domain distinct from the target domain from which the test examples are extracted, or the more general scenario of multiple source adaptation where training instances may have been collect from multiple source domains, all distinct from the target.

The topic of the Summer School also covers other important problems, e.g., sample bias correction and active learning, where the active distribution corresponding to the learner’s labeling request differs from the target distribution. Many other intermediate problems and scenarios appear in practice and will be all covered in this Summer School.

The research questions addressed by this Summer School are critical, ignoring them can lead to dramatically poor results. Some straightforward existing solutions based on importance weighting are typically not effective and can even worsen performance. Some of the questions addressed in this Summer School are: Which algorithms should be used for domain adaptation? Under what theoretical conditions will they be successful? How do these algorithms scale to large domain adaptation problems and how can they be applied to computer vision?



Course Credit