Constructive Feature Learning and the Development of Visual Expertise

We present a framework for learning features for visual discrimination. The learning system is exposed to a sequence of training images. Whenever it fails to recognize a visual context adequately, new features are sought that discriminate further between the true and false classes. Features consist of hierarchical combinations of primitive features (local edge and texture characteristics) that are sampled from example images. The system continues to learn better features even after all recognition errors have been eliminated, similarly to mechanisms underlying human visual expertise. Whenever the probabilistic recognition algorithm returns any posterior class probabilities greater than zero and less than one, the system attempts to find new features that improve discrimination between the classes in question. Our experiments indicate that this procedure tends to improve classification accuracy on independent test images, while reducing the number of features used for recognition.

• Type: Conference
• Year: 2000
• Where: ICML
• Authors: Justus H. Piater, Roderic A. Grupen
• Keywords: Human Visual Expertise, ICML 2000, Machine Learning, Posterior Class Probabilities, Probabilistic Recognition Algorithm