ML Anthology

Visual and Semantic Similarity in ImageNet

Thomas Deselaers, Vittorio Ferrari
CVPR 2011 pp. 1777-1784
doi:10.1109/CVPR.2011.5995474 /cvpr/2011/deselaers2011cvpr-visual/

Abstract

Many computer vision approaches take for granted positive answers to questions such as “Are semantic categories visually separable?” and “Is visual similarity correlated to semantic similarity?”. In this paper, we study experimentally whether these assumptions hold and show parallels to questions investigated in cognitive science about the human visual system. The insights gained from our analysis enable building a novel distance function between images assessing whether they are from the same basic-level category. This function goes beyond direct visual distance as it also exploits semantic similarity measured through ImageNet. We demonstrate experimentally that it outperforms purely visual distances.

PDF CVPR Semantic Scholar

Cite

Text

Deselaers and Ferrari. "Visual and Semantic Similarity in ImageNet." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995474

Markdown

[Deselaers and Ferrari. "Visual and Semantic Similarity in ImageNet." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/deselaers2011cvpr-visual/) doi:10.1109/CVPR.2011.5995474

BibTeX

@inproceedings{deselaers2011cvpr-visual,
  title     = {{Visual and Semantic Similarity in ImageNet}},
  author    = {Deselaers, Thomas and Ferrari, Vittorio},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {1777-1784},
  doi       = {10.1109/CVPR.2011.5995474},
  url       = {https://mlanthology.org/cvpr/2011/deselaers2011cvpr-visual/}
}