Learning to Adapt Across Multimedia Domains

In multimedia, machine learning techniques are often applied to build models to map low-level feature vectors into semantic labels. As data such as images and videos come from a variety of domains (e.g., genres, sources) with different distributions, there is a benefit of adapting models trained from one domain to other domains in terms of improving performance and reducing computational and human cost. In this thesis, we focus on a generic adaptation setting in multimedia, where supervised classifiers trained from one or more auxiliary domains are adapted to a new classifier that works well on a target domain with limited labeled examples. Our main contribution is a discriminative framework for function-level classifier adaptation based on regularized loss minimization, which adapts classifiers of any type by modifying their decision functions in an efficient and principled way. Two adaptation algorithms derived from this general framework, adaptive support vector machines (aSVM) and adaptive kernel logistic regression (aKLR), are discussed in details. We further extend this framework by integrating domain analysis approaches that measure and weight the utility of auxiliary domains, and sample selection methods that identify informative examples to help the adaptation process. The proposed approaches are evaluated on cross-domain video concept detection using the TRECVID corpus, where preliminary experiments have shown promising results. Our general approaches can be applied to other adaptation problems including retrieval model adaptation and cross-corpus text categorization. Thesis Committee: Alexander G. Hauptmann (Chair) Christos Faloutsos Jie Yang Shih-Fu Chang (Columbia University)