Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade

By Paul A. Viola, Michael J. Jones. Neural Information Processing Systems, 2001

603 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/5aff66011788597f5bcbe90a32b5f75fa0272c27

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer (2017, background): “Test (n=129 slides and images) RUMC 23 6 50 14 15 2 (1-14) 79”
Image Parsing: Unifying Segmentation, Detection, and Recognition (2003, unknown): “It is most convenient for us to use the AdaBoost approach ([20]) because of it effectivness and its probabilistic interpretation, see section (5).”
Large scale mining and retrieval of visual data in a multimodal context (2008, methodology): “It is based on an approach proposed in [Viola and Jones, 2001a] for Asymmetric Adaboost, but applied to Discrete Adaboost: before each”
Scene text detection and recognition: recent advances and future trends (2015, methodology): “The detector is a cascade Adaboost [42] classifier, in which each weak classifier is trained from a set of features.”
Calibrated asymmetric surrogate losses (2012, background): “For example, Adaboost is often applied to heavily imbalanced data sets where misclassification costs are label-dependent, such as in cascades for face detection [38].”
A Survey of Recent Advances in Face Detection (2010, background): “To handle the huge amount of negative training examples, Viola and Jones [92] used a bootstrap process.”
Adaptive Machine Learning for Credit Card Fraud Detection (2015, background): “Many cost-sensitive algorithms available in the literature are based on boosting; see for example AsymBoost [198], AdaCost [126], CSB [199], DataBoost [45], AdaUBoost [200] and SMOTEBoost [122].”
Cost-sensitive boosting for classification of imbalanced data (2007, background): “The cost of misclassifying a negative case is regarded as higher than misclassifying a positive sample [60].”
On-line Boosting and Vision (2006, background): “The seminal work of Viola and Jones [31] which applied boosting to robust and fast object detection tasks, paved the way of boosting in the area of computer vision, e.g. [18] [15] [30] [34].”
A survey on face detection in the wild: Past, present and future (2015, background): “…[61] [62] schemes GentleBoost[107] [66] FloatBoost[59] Reuseprevious Boostingchain[110] nodes'results Nestedcascade[61] Introduce AsymmetricBoosting[111] [112] [113] asymmetry Linearasymmetricclassifier[116] SetintermediateFixednodeperformance[107] thresholds WaldBoost[118] during…”
FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply (2020, background): “Model Cascades: Cascades consisting of a sequence of models are useful to balance the quality and runtime of inference [49, 50, 24, 36, 48, 51, 54, 38].”