Now showing items 1-2 of 2
Sprite Learning and Object Category Recognition using Invariant Features
This thesis explores the use of invariant features for learning sprites from image sequences, and for recognising object categories in images. A popular framework for the interpretation of image sequences is the layers ...
Active Learning - An Explicit Treatment of Unreliable Parameters
Active learning reduces annotation costs for supervised learning by concentrating labelling efforts on the most informative data. Most active learning methods assume that the model structure is fixed in advance and focus ...