ABSTRACT Title of dissertation: UNDERSTANDING OBJECTS IN THE VISUAL WORLD

One way to understand the visual world is by reasoning about the objects present in it: their type, their location, their similarities, their layout etc. Despite several suc-cesses, detailed recognition remains a challenging tasks for current computer vision sys-tems. This dissertation focuses on building systems that improve on the state-of-the-art on several fronts. On one hand, we propose better representations of visual categories that enable more accurate reasoning about their properties. To learn such representations, we employ machine learning methods that leverage the power of big-data. On the other hand, we present solutions to make current frameworks more efficient without losing on performance. The first part of the dissertation focuses on improvements in efficiency. We first introduce a fast automated mechanism for selecting a diverse set of discriminative fil-ters and show that one can efficiently learn a universal model of filter “goodness ” based on properties of the filter itself. As an alternative to the expensive evaluation of filters, which is often the bottleneck in many techniques, our method has the potential of dra-matically altering the trade-off between the accuracy of a filter based method and the cos