Unsupervised object category discovery via information bottleneck method

@inproceedings{Lou2010UnsupervisedOC,
  title={Unsupervised object category discovery via information bottleneck method},
  author={Zhengzheng Lou and Yangdong Ye and Dong Liu},
  booktitle={ACM Multimedia},
  year={2010}
}
We present a novel approach to automatically discover object categories from a collection of unlabeled images. This is achieved by the Information Bottleneck method, which finds the optimal partitioning of the image collection by maximally preserving the relevant information with respect to the latent semantic residing in the image contents. In this method, the images are modeled by the Bag-of-Words representation, which naturally transforms each image into a visual document composed of visual… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-4 of 4 references

Similar Papers

Loading similar papers…