The increasing prominence of weakly labeled data nurtures a growing demand for object detection methods that can cope with minimal supervision. We propose an approach that automatically identifies discriminative configurations of visual patterns that are characteristic of a given object class. We formulate the problem as a constrained submodular optimization problem and demonstrate the benefits of the discovered configurations in remedying mislocalizations and finding informative positive and negative training examples. Together, these lead to state-of-the-art weakly-supervised detection results on the challenging PASCAL VOC dataset.
@article{arxiv.1406.6507,
title = {Weakly-supervised Discovery of Visual Pattern Configurations},
author = {Hyun Oh Song and Yong Jae Lee and Stefanie Jegelka and Trevor Darrell},
journal= {arXiv preprint arXiv:1406.6507},
year = {2014}
}