Decomposition, discovery and detection of visual categories using topic models

We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and low dimensional representation for multiple visual categories from multiple view points without labeling of the training instances. The learnt object components range from local structures over line segments to global silhouette-like descriptions. This representation can be used to discover object categories in a totally unsupervised fashion. Furthermore we employ the representation as the basis for building a supervised multi-category detection system making efficient use of training examples and outperforming pure features-based representations. The proposed speed-ups make the system scale to large databases. Experiments on three databases show that the approach improves the state-of-the-art in unsupervised learning as well as supervised detection. In particular we improve the stateof-the-art on the challe...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Mario Fritz, Bernt Schiele
• Keywords: Computer Vision, CVPR 2008, Multi-class Detection Tasks, Multiple Visual Categories, Supervised Detection, Supervised Multi-category Detection, Visual Object Categories