Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade

@inproceedings{Viola2001FastAR,
  title={Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade},
  author={Paul A. Viola and Michael J. Jones},
  booktitle={NIPS},
  year={2001}
}
This paper develops a new approach for extremely fast detection in domains where the distribution of positive and negative examples is highly skewed (e.g. face detection or database retrieval). In such domains a cascade of simple classifiers each trained to achieve high detection rates and modest false positive rates can yield a final detector with many desirable features: including high detection rates, very low false positive rates, and fast performance. Achieving extremely high detection… CONTINUE READING

Results and Topics from this paper.

Key Quantitative Results

  • The final face detection system can process 15 frames per second, achieves over 90% detection, and a false positive rate of 1 in a 1,000,000.

Citations

Publications citing this paper.
SHOWING 1-10 OF 363 CITATIONS, ESTIMATED 23% COVERAGE

Cost-sensitive boosting: a unified approach

VIEW 23 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2016
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Efficient Pedestrian Detection by Directly Optimizing the Partial Area under the ROC Curve

  • 2013 IEEE International Conference on Computer Vision
  • 2013
VIEW 9 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Imbalanced data classification algorithm based on boosting and cascade model

  • 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
  • 2012
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

The ROC-Boost Design Algorithm for Asymmetric Classification

  • 2011 10th International Conference on Machine Learning and Applications and Workshops
  • 2011
VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2002
2019

CITATION STATISTICS

  • 95 Highly Influenced Citations

  • Averaged 16 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 10 REFERENCES

Schapire and Yoram Singer . Improved boosting algorithms using confidencerated predictions

E. Robert
  • Machine Learning
  • 1999

Neural Network-Based Face Detection

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 1998
VIEW 2 EXCERPTS

Schapire . A decisiontheoretic generalization of on - line learning and an application to boosting

Yoav Freund, E. Robert
  • Computational Learning Theory : Eurocolt ’
  • 1995

Similar Papers

Loading similar papers…