4 accepted papers
Self-supervised learning models extract general-purpose representations from data. Quantifying the reliability of these representations is crucial, as many downstream models rely on them as input for their own tasks. To this end, we introduce a formal definition of _representation reliability_: the…
In machine learning, disparity metrics are often defined by measuring the difference in the performance or outcome of a model, across different sub-populations (groups) of datapoints. Thus, the inputs to disparity quantification consist of a model's predictions y', the ground-truth labels for the pr…
Videos recorded from first person (egocentric) perspective have little visual appearance in common with those from third person perspective, especially with videos captured by top-view surveillance cameras. In this paper, we aim to relate these two sources of information from a surveillance standpoi…
The availability of GIS (Geographical Information System) databases for many urban areas, provides a valuable source of information for improving the performance of many computer vision tasks. In this paper, we propose a method which leverages information acquired from GIS databases to perform seman…