Incremental learning of object detectors using a visual shape alphabet
- 10 July 2006
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 3-10
- https://doi.org/10.1109/cvpr.2006.153
Abstract
We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and for the complexity of the multiclass system to grow sublinearly with the number of categories. To this end we introduce a visual alphabet representation which can be learnt incrementally, and explicitly shares boundary fragments (contours) and spatial configurations (relation to centroid) across object categories. We develop a learning algorithm with the following novel contributions: (i) AdaBoost is adapted to learn jointly, based on shape features; (ii) a new learning schedule enables incremental additions of new categories; and (iii) the algorithm learns to detect objects (instead of categorizing images). Furthermore, we show that category similarities can be predicted from the alphabet. We obtain excellent experimental results on a variety of complex categories over several visual aspects. We show that the sharing of shape features not only reduces the number of features required per category, but also often improves recognition performance, as compared to individual detectors which are trained on a per-class basis.Keywords
This publication has 9 references indexed in Scilit:
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categoriesComputer Vision and Image Understanding, 2007
- Generic object recognition with boostingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Cross-Generalization: Learning Novel Classes from a Single Example by Feature ReplacementPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- An Evaluation of Local Shape-Based Features for Pedestrian DetectionPublished by British Machine Vision Association and Society for Pattern Recognition ,2005
- Contour-based learning for object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Sharing features: efficient boosting procedures for multiclass object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Object class recognition by unsupervised scale-invariant learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Detecting lameness using ‘Re-sampling Condensation’ and ‘multi-stream cyclic hidden Markov models’Image and Vision Computing, 2002
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997