EM-DD: An Improved Multiple-Instance Learning Technique

@inproceedings{Zhang2001EMDDAI,
  title={EM-DD: An Improved Multiple-Instance Learning Technique},
  author={Qi Zhang and Sally A. Goldman},
  booktitle={NIPS},
  year={2001}
}
We present a new multiple-instance (MI) learning technique (EMDD) that combines EM with the diverse density (DD) algorithm. EM-DD is a general-purpose MI algorithm that can be applied with boolean or real-value labels and makes real-value predictions. On the boolean Musk benchmarks, the EM-DD algorithm without any tuning significantly outperforms all previous algorithms. EM-DD is relatively insensitive to the number of relevant attributes in the data set and scales up well to large bag sizes… CONTINUE READING
Highly Influential
This paper has highly influenced 126 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 866 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 435 extracted citations

866 Citations

050'01'04'08'12'16
Citations per Year
Semantic Scholar estimates that this publication has 866 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 13 references

Learning single and multiple instance decision trees for computer security applications

  • G. Ru o
  • Doctoral dissertation. Department of Computer…
  • 2000
Highly Influential
4 Excerpts

A framework for multiple-instance learning

  • O. Maron, T. Lozano-P erez
  • Neural Information Processing Systems
  • 1998
Highly Influential
7 Excerpts

Similar Papers

Loading similar papers…