Transfer learning for image classification with sparse prototype representations
Author(s)
Quattoni, Ariadna
Collins, Michael
Darrell, Trevor
Advisor(s)
Trevor Darrell
Date Issued
March 3, 2008
Abstract
To learn a new visual category from few examples, prior knowledge from unlabeled data as well as previous related categories may be useful. We develop a new method for transfer learning which exploits available unlabeled data and an arbitrary kernel function; we form a representation based on kernel distances to a large set of unlabeled data points. To transfer knowledge from previous related problems we observe that a category might be learnable using only a small subset of reference prototypes. Related problems may share a significant number of relevant prototypes; we find such a reduced representation by performing a joint loss minimization over the training sets of related problems with a shared regularization penalty that minimizes the total number of prototypes involved in the approximation.This optimization problem can be formulated as a linear program thatcan be solved efficiently. We conduct experiments on a news-topic prediction task where the goal is to predict whether an image belongs to a particularnews topic. Our results show that when only few examples are available for training a target topic, leveraging knowledge learnt from other topics can significantly improve performance.
Subjects
transfer learning
image classification
Persistent DSpace Link
