ML Anthology

Low-Shot Learning with Large-Scale Diffusion

Matthijs Douze, Arthur Szlam, Bharath Hariharan, Hervé Jégou
CVPR 2018
doi:10.1109/CVPR.2018.00353 /cvpr/2018/douze2018cvpr-lowshot/

Abstract

This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time. This setup is often referred to as low-shot learning, where a standard approach is to re-train the last few layers of a convolutional neural network learned on separate classes for which training examples are abundant. We consider a semi-supervised setting based on a large collection of images to support label propagation. This is possible by leveraging the recent advances on large-scale similarity graph construction. We show that despite its conceptual simplicity, scaling label propagation up to hundred millions of images leads to state of the art accuracy in the low-shot learning regime.

PDF CVPR Semantic Scholar

Cite

Text

Douze et al. "Low-Shot Learning with Large-Scale Diffusion." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00353

Markdown

[Douze et al. "Low-Shot Learning with Large-Scale Diffusion." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/douze2018cvpr-lowshot/) doi:10.1109/CVPR.2018.00353

BibTeX

@inproceedings{douze2018cvpr-lowshot,
  title     = {{Low-Shot Learning with Large-Scale Diffusion}},
  author    = {Douze, Matthijs and Szlam, Arthur and Hariharan, Bharath and Jégou, Hervé},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00353},
  url       = {https://mlanthology.org/cvpr/2018/douze2018cvpr-lowshot/}
}