Foreground Focus: Unsupervised Learning from Partially Matching Images

  title={Foreground Focus: Unsupervised Learning from Partially Matching Images},
  author={Yong Jae Lee and Kristen Grauman},
  journal={International Journal of Computer Vision},
We present a method to automatically discover meaningful features in unlabeled image collections. Each image is decomposed into semi-local features that describe neighborhood appearance and geometry. The goal is to determine for each image which of these parts are most relevant, given the image content in the remainder of the collection. Our method first computes an initial image-level grouping based on feature correspondences, and then iteratively refines cluster assignments based on the… CONTINUE READING

19 Figures & Tables



Citations per Year

131 Citations

Semantic Scholar estimates that this publication has 131 citations based on the available data.

See our FAQ for additional information.