P-N learning: Bootstrapping binary classifiers by structural constraints
Zdenek Kalal, Jiřı́ Matas, Krystian Mikolajczyk · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2010
This paper shows that the performance of a binary classifier can be significantly improved by the processing of structured unlabeled data, i.e. data are structured if knowing the label of one example restricts the labeling of the others. We propose a novel paradigm for training a binary classifier from labeled and unlabeled examples that we call P-N learning. The learning process is guided by positive (P) and negative (N) constraints which restrict the labeling of the unlabeled set. P-N learning evaluates the classifier on the unlabeled data, identifies examples that have been classified in contradiction with structural constraints and augments the training set with the corrected samples in an iterative process. We propose a theory that formulates the conditions under which P-N learning guarantees improvement of the initial classifier and validate it on synthetic and real data. P-N learning is applied to the problem of on-line learning of object detector during tracking. We show that an accurate object detector can be learned from a single example and an unlabeled video sequence where the object may occur. The algorithm is compared with related approaches and state-of-the-art is achieved on a variety of objects (faces, pedestrians, cars, motorbikes and animals).
Cited by 1,023 works. doi:10.1109/cvpr.2010.5540231 Open-access PDF
Authors
References
- Random Forests
- Rapid object detection using a boosted cascade of simple features
- An Iterative Image Registration Technique with an Application to Stereo Vision
- Object class recognition by unsupervised scale-invariant learning
- Combining labeled and unlabeled data with co-training
- Robust and optimal control
- Robust and Optimal Control
- Text Classification from Labeled and Unlabeled Documents using EM
- Robust and optimal control
- Semi-Supervised Learning