Unsupervised Detection and Segmentation of Identical Objects

Minsu Cho, Young Min Shin, Kyoung Mu Lee

CVPR 2010 pp. 1617-1624

doi:10.1109/CVPR.2010.5539777 /cvpr/2010/cho2010cvpr-unsupervised/

Abstract

We address an unsupervised object detection and segmentation problem that goes beyond the conventional assumptions of one-to-one object correspondences or modeltest settings between images. Our method can detect and segment identical objects directly from a single image or a handful of images without any supervision. To detect and segment all the object-level correspondences from the given images, a novel multi-layer match-growing method is proposed that starts from initial local feature matches and explores the images by intra-layer expansion and inter-layer merge. It estimates geometric relations between object entities and establishes ‘object correspondence networks’ that connect matching objects. Experiments demonstrate robust performance of our method on challenging datasets.

CVPR Semantic Scholar

Cite

Text

Cho et al. "Unsupervised Detection and Segmentation of Identical Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539777

Markdown

[Cho et al. "Unsupervised Detection and Segmentation of Identical Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/cho2010cvpr-unsupervised/) doi:10.1109/CVPR.2010.5539777

BibTeX

@inproceedings{cho2010cvpr-unsupervised,
  title     = {{Unsupervised Detection and Segmentation of Identical Objects}},
  author    = {Cho, Minsu and Shin, Young Min and Lee, Kyoung Mu},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {1617-1624},
  doi       = {10.1109/CVPR.2010.5539777},
  url       = {https://mlanthology.org/cvpr/2010/cho2010cvpr-unsupervised/}
}