FloatBoost learning and statistical face detection
Abstract
A novel learning procedure, called FloatBoost, is proposed for learning a boosted classifier for achieving the minimum error rate. FloatBoost learning uses a backtrack mechanism after each iteration of AdaBoost learning to minimize the error rate directly, rather than minimizing an exponential function of the margin as in the traditional AdaBoost algorithms. A second contribution of the paper is a novel statistical model for learning best weak classifiers using a stagewise approximation of the posterior probability. These novel techniques lead to a classifier which requires fewer weak classifiers than AdaBoost yet achieves lower error rates in both training and testing, as demonstrated by extensive experiments. Applied to face detection, the FloatBoost learning method, together with a proposed detector pyramid architecture, leads to the first real-time multiview face detection system reported.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The essence of cascade is to learn more discriminative classifiers by using multistage classifiers, such that early stages discard a large number of easy negative samples so that later stages can focus on handling more difficult examples.
“The essence of cascade (Felzenszwalb et al. 2010a;Bourdev and Brandt 2005;Li and Zhang 2004) is to learn more discriminative classifiers by using multistage classifiers, such that early stages discard a large number of easy negative samples so that later stages can focus on handling more difficult examples.”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Li and Zhang 2004
Cites
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731 · see citing works
A decision-theoretic generalization of on-line learning and an application to boosting
Freund, Y., & Schapire, R. E. (1997) · Journal of Computer and System Sciences · doi:10.1006/jcss.1997.1504 · Cited by 20,466 · see citing works
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300 · see citing works
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · see citing works
Friedman, J., Hastie, T., & Tibshirani, R. (2000) · The Annals of Statistics · doi:10.1214/aos/1016218223 · Cited by 6,884 · see citing works
Valiant, L. G. (1984) · ACM eBooks · doi:10.1145/3749740.3749746 · Cited by 4,211 · see citing works
Neural network-based face detection
Rowley, H. A., Baluja, S., & Kanade, T. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.655647 · Cited by 3,554 · see citing works
Valiant, L. G. (1984) · Communications of the ACM · doi:10.1145/1968.1972 · Cited by 3,279 · see citing works
Floating search methods in feature selection
Pudil, P., Novovičová, J., & Kittler, J. (1994) · Pattern Recognition Letters · doi:10.1016/0167-8655(94)90127-9 · Cited by 3,129 · see citing works
An extended set of Haar-like features for rapid object detection
Lienhart, R., & Maydt, J. (2003) · Proceedings. International Conference on Image Processing · doi:10.1109/icip.2002.1038171 · Cited by 2,977 · cited 1× · see citing works
“A coarse-to-fine view-partition strategy is used and this leads to a detector-pyramid architecture consisting of several levels from the coarse level on the top to the fine level at the bottom.”
MethodFace recognition by elastic bunch graph matching
Wiskott, L., Fellous, J., Kuiger, N., & von der Malsburg, C. (1997) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.598235 · Cited by 2,888 · see citing works
Improved boosting algorithms using confidence-rated predictions
Schapire, R. E., & Singer, Y. (1998) · Conference on Learning Theory · doi:10.1145/279943.279960 · Cited by 2,549 · see citing works
Boosting the margin: a new explanation for the effectiveness of voting methods
Bartlett, P. L., Freund, Y., Lee, W. S., & Schapire, R. E. (1998) · The Annals of Statistics · doi:10.1214/aos/1024691352 · Cited by 2,541 · see citing works
Training support vector machines: an application to face detection
Osuna, E., Freund, R. M., & Girosi, F. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1997.609310 · Cited by 2,481 · see citing works
Robust real-time object detection.
Viola, P. A. (2001) · Cited by 2,340 · see citing works
Feature selection: evaluation, application, and small sample performance
Jain, A. K., & Zongker, D. E. (1997) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.574797 · Cited by 2,186 · see citing works
Li, S. Z., Jain, A. K., Deng, J., & service), S. (. (2011) · Springer eBooks · doi:10.1007/978-0-85729-932-1 · Cited by 1,849 · see citing works
Self-citationView-based and modular eigenspaces for face recognition
Pentland, Moghaddam, & Starner (1994) · doi:10.1109/cvpr.1994.323814 · Cited by 1,806 · see citing works
Face Recognition by Elastic Bunch Graph Matching*†
Wiskott, L., Fellous, J., Krüger, N., & von der Malsburg, C. (2022) · Routledge eBooks · doi:10.1201/9780203750520-11 · Cited by 1,781 · see citing works
Example-based learning for view-based human face detection
Sung, K. K., & Poggio, T. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.655648 · Cited by 1,779 · see citing works
An Introduction to Computational Learning Theory
Kearns, M. J., & Vazirani, U. (1994) · doi:10.7551/mitpress/3897.001.0001 · Cited by 1,697 · see citing works
Probabilistic visual learning for object representation
Moghaddam, B., & Pentland, A. (1997) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.598227 · Cited by 1,444 · see citing works
A general framework for object detection
Papageorgiou, C., Oren, M., & Poggio, T. (2002) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.1998.710772 · Cited by 1,437 · see citing works
Summed-area tables for texture mapping
Crow, F. C. (1984) · ACM SIGGRAPH Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH) · doi:10.1145/800031.808600 · Cited by 1,134 · see citing works
Arcing classifier (with discussion and a rejoinder by the author)
Breiman, L. (1998) · The Annals of Statistics · doi:10.1214/aos/1024691079 · Cited by 1,104 · see citing works
A statistical method for 3D object detection applied to faces and cars
Schneiderman, H., & Takeo Kanade, A. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2000.855895 · Cited by 1,059 · see citing works
Hjelmås, E., & Low, B. (2001) · Computer Vision and Image Understanding · doi:10.1006/cviu.2001.0921 · Cited by 936 · see citing works
Li, S. Z., & Jain, A. K. (2005) · Springer eBooks · doi:10.1007/b138828 · Cited by 791 · see citing works
Self-citationSummed-area tables for texture mapping
Crow, F. C. (1984) · ACM SIGGRAPH Computer Graphics · doi:10.1145/964965.808600 · Cited by 660 · see citing works
Statistical Learning of Multi-view Face Detection
Li, S. Z., Zhu, L., Zhang, Z., Blake, A., Zhang, H., & Shum, H. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47979-1_5 · Cited by 404 · see citing works
Self-citationTieu, K. H., & Viola, P. A. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2000.855824 · Cited by 390 · see citing works
Object Detection Using the Statistics of Parts
Schneiderman, H., & Takeo Kanade, A. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000011202.85607.00 · Cited by 356 · see citing works
Transformation Invariance in Pattern Recognition – Tangent Distance and Tangent Propagation
Simard, P. Y., LeCun, Y., Denker, J. S., & Victorri, B. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35289-8_17 · Cited by 348 · see citing works
Yang, M., Roth, D., & Ahuja, N. (1999) · Cited by 312 · see citing works
Adaptive floating search methods in feature selection
Somol, P., Pudil, P., Novovičová, J., & Paclı́k, P. (1999) · Pattern Recognition Letters · doi:10.1016/s0167-8655(99)00083-5 · Cited by 305 · see citing works
Functional Gradient Techniques for Combining Hypotheses
Mason, L., Baxter, J., Bartlett, P. L., & Frean, M. R. (2000) · The MIT Press eBooks · doi:10.7551/mitpress/1113.003.0017 · Cited by 276 · see citing works
Fleuret, F., & Geman, D. (2001) · International Journal of Computer Vision · doi:10.1023/a:1011113216584 · Cited by 273 · see citing works
A bayesian discriminating features method for face detection
Liu, C. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1201822 · Cited by 245 · see citing works
A statistical approach to 3d object detection applied to faces and cars
Schneiderman, H., & Takeo Kanade, A. (2000) · Cited by 243 · see citing works
Support vector regression and classification based multi-view face detection and recognition
Li, Y., Gong, S., & Liddell, H. (2002) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/afgr.2000.840650 · Cited by 236 · see citing works
Transformation Invariance in Pattern Recognition — Tangent Distance and Tangent Propagation
Simard, P. Y., LeCun, Y., Denker, J. S., & Victorri, B. (1998) · Lecture notes in computer science · doi:10.1007/3-540-49430-8_13 · Cited by 233 · see citing works
Kuchinsky, A., Pering, C., Creech, M. L., Freeze, D. F., Serra, B., & Jacek Gwizdka, A. (1999) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/302979.303143 · Cited by 202 · see citing works
Joint induction of shape features and tree classifiers
Amit, Y., Geman, D., & Wilder, K. (1997) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.632990 · Cited by 200 · see citing works
Face pose discrimination using support vector machines (SVM)
Huang, J., Shao, X., & Wechsler, H. (2002) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.1998.711102 · Cited by 190 · see citing works
Transformation invariance in pattern recognition: Tangent distance and propagation
Simard, P. Y., LeCun, Y., Denker, J. S., & Victorri, B. (2000) · International Journal of Imaging Systems and Technology · doi:10.1002/1098-1098(2000)11:3 · Cited by 151 · see citing works
Boxlets: A Fast Convolution Algorithm for Signal Processing and Neural Networks
Simard, P., Bottou, L., Haffner, P., et al. (1998) · Cited by 129 · see citing works
Human Face Recognition and the Face Image Set′s Topology
Bichsel, M., & Pentland, A. ‘. (1994) · CVGIP Image Understanding · doi:10.1006/ciun.1994.1017 · Cited by 117 · see citing works
A Gradient-Based Boosting Algorithm for Regression Problems
Zemel, R. S., & Pitassi, T. (2000) · Cited by 110 · see citing works
An investigation into face pose distributions
Gong, S., McKenna, S. J., & Collins, J. J. (2002) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/afgr.1996.557275 · Cited by 91 · see citing works
FloatBoost Learning for Classification
Li, S. Z., Zhen-qiu, Z., Shum, H., & Zhang, H. (2002) · Cited by 67 · see citing works
Self-citationNg, J., & Gong, S. (2003) · doi:10.1109/ratfg.1999.799218 · Cited by 64 · see citing works
A fast and accurate face detector for indexation of face images
Féraud, R., Bernier, O., Viallet, J. E., & Collobert, M. (2002) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/afgr.2000.840615 · Cited by 58 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01247-4 · Cited by 2,965 · see citing works
Tu, Z. (2005) · Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 · doi:10.1109/iccv.2005.194 · Cited by 397 · see citing works
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2018) · arXiv · doi:10.48550/arxiv.1809.02165 · Cited by 2,965 · see citing works
Hao, Z., Liu, Y., Qin, H., Yan, J., Li, X., & Hu, X. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.207 · Cited by 134 · see citing works
- Authors
- Li, S. Z., & Zhang, Z.
- Affiliations
- Microsoft Research Asia (China) (CN)
- University of Illinois Urbana-Champaign (US)
- ORCID
- Li, S.Z.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2004-09
- Volume
- 26
- Issue
- 9
- Pages
- 1112-1123
- ISSN
- 0162-8828 (ISSN-L)
- OpenAlex
- W2140274257
- Cited by
- 525
- References
- 52
- Citations by year
- 2026: 2 · 2025: 1 · 2024: 1 · 2023: 2 · 2022: 4 · 2021: 6 · 2020: 7 · 2019: 14 · 2018: 10 · 2017: 20 · 2016: 11 · 2015: 23 · 2014: 34 · 2013: 25 · 2012: 43
- FWCI
- 43.21
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- AdaBoost, boosting, error rate minimization, weak classifier selection, real-time face detection
- MeSH terms
- Algorithms, Artificial Intelligence, Computer Simulation, Face, Humans, Image Enhancement, Image Interpretation, Computer-Assisted, Models, Biological, Pattern Recognition, Automated, Sensitivity and Specificity, Reproducibility of Results, Models, Statistical, Cluster Analysis, Information Storage and Retrieval
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
