Recognizing the presence of object classes in an image, or image classification, has become an increasingly important topic of interest. Equally important, however, is also the capability to locate these object classes in the image. The combined problem, usually referred to as object layout, is approached with models that require intense training. In (Lim et al., 2011) this issue is addressed with the primary goal of minimizing the training requirements so as to allow for ease of adding new object classes, as opposed to approaches that favor training a suite of object-specific classifiers. It turns out that it is possible to effectively represent an object class with enough image exemplars, in combination with image retrieval techniques, and statistical modeling, to obtain state-of-the-art object recognition performance with minimal training efforts.


  1. ISVC
    Multi-class Object Layout with Unsupervised Image Classification and Object Localization Lim, S., Doretto, G., and Rittscher, J. In International Symposium on Visual Computing, 2011. Oral abstract bibTeX pdf