Incremental Learning of Visual Categories
Incremental learning of visual categories denotes the capability of a visual perceptual system to build up an increasing repertoire of visual concepts based on a sequence of experiences. A visual category is here defined as a possibly large group of individual objects that share similar properties like shape, appearance, or color. Biological visual systems achieve this function very efficiently for their behaviorally relevant categories, where an appropriate generation and selection of features is considered to be responsible for good generalization. Static visual learning models with a fixed a priori set of trainable parameters face severe problems for dynamically changing training sets. In contrast to non-incremental visual approaches, incremental ones approach this problem by growing categorical representations that adapt to successively available training stimuli.
Visual categories can be differentiated according to their abstraction level into...
- Fritz, M. (2008). Modeling, representation and learning of Visual Categories. Ph.D. thesis, Technical University of Darmstadt.Google Scholar
- Hasler, S., Wersing, H., & Körner, E. (2007). A comparison of features in parts-based object recognition hierarchies. In Proceedings of International Conference on Artificial Neural Networks (pp. 210–219).Google Scholar
- Leibe, B., Leonardis, A., & Schiele, B. (2004). Combined object categorization and segmentation with an implicit shape model. ECCV workshop on statistical learning in computer vision (pp. 17–32). Prague.Google Scholar
- Mikolajczyk, K., Leibe, B., & Schiele, B. (2006). Multiple object class detection with a generative model. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 26–36). San Francisco.Google Scholar
- Ng, A. Y., & Jordan, M. I. (2001). On discriminative vs. generative classifiers: A comparison of logistic regression and naive Bayes. In Proceedings of the advances in neural information processing systems (pp. 849–856).Google Scholar
- Vapnik, V. (2000). The nature of statistical learning theory. New York: Springer.Google Scholar