IEEE Conference on Computer Vision and Pattern Recognition 2014
Learning Inhomogeneous FRAME Models for Object Patterns
University of California, Los Angeles (UCLA), USA
Google Inc, USA
We investigate an inhomogeneous version of the FRAME (Filters, Random field, And Maximum Entropy) model and apply it to modeling object patterns. The inhomogeneous FRAME is a non-stationary Markov random field model that reproduces the observed marginal distributions or statistics of filter responses at all the different locations, scales and orientations. Our experiments show that the inhomogeneous FRAME model is capable of generating a wide variety of object patterns in natural images. We then propose a sparsified version of the inhomogeneous FRAME model where the model reproduces observed statistical properties of filter responses at a small number of selected locations, scales and orientations. We propose to select these locations, scales and orientations by a shared sparse coding scheme, and we explore the connection between the sparse FRAME model and the linear additive sparse coding model. Our experiments show that it is possible to learn sparse FRAME models in unsupervised fashion and the learned models are useful for object classification.
Exp 1: Synthesis by dense FRAME
Exp 2: Synthesis by sparse FRAME
Exp 3: Detection by Sparse FRAME
Exp 4: Clustering by Sparse FRAME
Exp 5: Clustering Evaluation
Exp 8: Domain Transfer
Go to reproducibility page for IJCV paper for more results.
The work is supported by NSF DMS 1310391, ONR MURI N00014-10-1-0933, DARPA MSEE FA8650-11-1-7149.