Article ID Journal Published Year Pages File Type
527103 Image and Vision Computing 2012 16 Pages PDF
Abstract
► We extend import vector machines (IVM) to an incremental learner (I2VM). ► We exploit the reconstructive component in the discriminative IVM learner. ► I2VM can deal with real or pseudo-concept-drifts in the data distribution. ► I2VM is competitive or superior to IVM and other incremental learners.
Related Topics
Physical Sciences and Engineering Computer Science Computer Vision and Pattern Recognition
Authors
, , ,