ICML 2011 workshop on unsupervised and transfer learning

Transfer Learning with Applications to Multiclass Object Detection
Ruslan Salakhutdinov
MIT, Massachussetts, USA

We present a hierarchical Bayesian classification model that is able to transfer higher-level structure, abstracted from object categories that have many training examples, to learning novel visual categories with only a few training examples. Unlike many of the existing object detection and recognition systems that treat different classes as unrelated entities, our model learns both a hierarchy for sharing visual appearance across 200 object categories and hierarchical parameters. We demonstrate on the challenging object localization and detection task that the proposed model substantially improves the accuracy of the standard single object detectors that ignore hierarchical structure altogether.