Principal Investigator Stefanie Jegelka
Learning to localize objects in images is a fundamental problem in computer vision. For this problem (as for many others), we are increasingly faced with the problem that accurately labeled training data is expensive and hence scarce. Therefore, we desire algorithms that are robust to weak labelings, i.e., image-level labels of the nature "the object is present" (instead of object locations). We address this problem via a combination of combinatorial and convex optimization: a discriminative submodular cover problem and a smoothed SVM formulation.