International Journal of Computer Vision

Learning Sparse FRAME Models for Natural Image Patterns

Jianwen Xie 1   Wenze Hu 2    Song-Chun Zhu 1    Ying Nian Wu 1

1 University of California, Los Angeles (UCLA), USA     2 Google Inc, USA


Reproducing Experiments

 

Section 1: Dense FRAME

Exp 1: Synthesis by Dense FRAME

Exp 2: Alignment by Dense FRAME

Exp 3: Clustering by Dense FRAME (with DoG)

Section 2: Sparse FRAME

Exp 4: Wavelet Selection by Shared Matching Pursuit

Exp 5: Synthesis by Sparse FRAME (regular MP)

Exp 6: Synthesis by Sparse FRAME (orthogonal MP)

Exp 7: Geometric Transformation

Exp 8: Detection by Sparse FRAME

Exp 9: Learning from 100+ Images with Automatic Alignment

Exp 10: Clustering by Sparse FRAME (without DoG)

Exp 11: Clustering by Sparse FRAME (with DoG)

Exp 12: Numerical Evaluation on Clustering

Exp 13: Unsupervised Learning of Codebooks (reconstruction)

Exp 14: Unsupervised Learning of Codebooks (sketching)

Exp 15: Binary Classification

Exp 16: Multi-class Classification

Exp 17: Domain Transfer


The work is supported by NSF DMS 1310391, ONR MURI N00014-10-1-0933, DARPA MSEE FA8650-11-1-7149.