On the computational rationale for generative models
On the computational rationale for generative models
A. Pece
2007 · DOI: 10.1016/j.cviu.2006.10.002
Computer Vision and Image Understanding · 7 Citations
TLDR
This paper uses a definition of generative and discriminative models to argue that, in some practical cases, generative models need to be formulated in order to be implemented within generate-and-test algorithms.