ML Anthology

Comparing Data-Dependent and Data-Independent Embeddings for Classification and Ranking of Internet Images

Yunchao Gong, Svetlana Lazebnik
CVPR 2011 pp. 2633-2640
doi:10.1109/CVPR.2011.5995619 /cvpr/2011/gong2011cvpr-comparing/

Abstract

This paper presents a comparative evaluation of feature embeddings for classification and ranking in large-scale Internet image datasets. We follow a popular framework for scalable visual learning, in which the data is first transformed by a nonlinear embedding and then an efficient linear classifier is trained in the resulting space. Our study includes data-dependent embeddings inspired by the semi-supervised learning literature, and data-independent ones based on approximating specific kernels (such as the Gaussian kernel for GIST features and the histogram intersection kernel for bags of words). Perhaps surprisingly, we find that data-dependent embeddings, despite being computed from large amounts of unlabeled data, do not have any advantage over data-independent ones in the regime of scarce labeled data. On the other hand, we find that several data-dependent embeddings are competitive with popular data-independent choices for large-scale classification.

CVPR Semantic Scholar

Cite

Text

Gong and Lazebnik. "Comparing Data-Dependent and Data-Independent Embeddings for Classification and Ranking of Internet Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995619

Markdown

[Gong and Lazebnik. "Comparing Data-Dependent and Data-Independent Embeddings for Classification and Ranking of Internet Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/gong2011cvpr-comparing/) doi:10.1109/CVPR.2011.5995619

BibTeX

@inproceedings{gong2011cvpr-comparing,
  title     = {{Comparing Data-Dependent and Data-Independent Embeddings for Classification and Ranking of Internet Images}},
  author    = {Gong, Yunchao and Lazebnik, Svetlana},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {2633-2640},
  doi       = {10.1109/CVPR.2011.5995619},
  url       = {https://mlanthology.org/cvpr/2011/gong2011cvpr-comparing/}
}