Hierarchical Subquery Evaluation for Active Learning on a Graph

  title={Hierarchical Subquery Evaluation for Active Learning on a Graph},
  author={Oisin Mac Aodha and Neill D. F. Campbell and Jan Kautz and Gabriel J. Brostow},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
To train good supervised and semi-supervised object classifiers, it is critical that we not waste the time of the human experts who are providing the training labels. Existing active learning strategies can have uneven performance, being efficient on some datasets but wasteful on others, or inconsistent just between runs on the same dataset. We propose perplexity based graph construction and a new hierarchical subquery evaluation algorithm to combat this variability, and to release the… CONTINUE READING
Highly Cited
This paper has 65 citations. REVIEW CITATIONS


Publications citing this paper.

66 Citations

Citations per Year
Semantic Scholar estimates that this publication has 66 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 42 references

Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions

  • X. Zhu, J. Lafferty, Z. Ghahramani
  • ICML workshops
  • 2003
Highly Influential
9 Excerpts

Active Frame

  • V. Karasev, A. Ravichandran, S. Soatto
  • Location, and Detector Selection for Automated…
  • 2014
1 Excerpt

Similar Papers

Loading similar papers…