Online domain adaptation of a pre-trained cascade of classifiers
- 1 June 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 577-584
- https://doi.org/10.1109/cvpr.2011.5995317
Abstract
Many classifiers are trained with massive training sets only to be applied at test time on data from a different distribution. How can we rapidly and simply adapt a classifier to a new test distribution, even when we do not have access to the original training data? We present an on-line approach for rapidly adapting a “black box” classifier to a new test data set without retraining the classifier or examining the original optimization criterion. Assuming the original classifier outputs a continuous number for which a threshold gives the class, we reclassify points near the original boundary using a Gaussian process regression scheme. We show how this general procedure can be used in the context of a classifier cascade, demonstrating performance that far exceeds state-of-the-art results in face detection on a standard data set. We also draw connections to work in semi-supervised learning, domain adaptation, and information regularization.Keywords
This publication has 7 references indexed in Scilit:
- Learning to re-rankPublished by Association for Computing Machinery (ACM) ,2011
- Domain adaptive bootstrapping for named entity recognitionPublished by Association for Computational Linguistics (ACL) ,2009
- Domain Adaptation for Statistical ClassifiersJournal of Artificial Intelligence Research, 2006
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004
- Probabilistic modeling of local appearance and spatial relationships for object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Neural network-based face detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Example-based learning for view-based human face detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998