English

Weakly-supervised Discovery of Visual Pattern Configurations

Computer Vision and Pattern Recognition 2014-06-26 v1 Machine Learning

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-22T04:46:42.686Z