In our work, we introduce the iterated Levenberg-Marquardt algorithm for solving MDS, and study the MDS feature learning with IMage Euclidean Distance (IMED) and Spatial Pyramid Matching (SPM) distance. We present experiments on both synthetic data and real images — the publicly accessible UIUC car image dataset. The MDS features based on SPM distance achieve exceptional performance for the car recognition task.
- Quan Wang, Kim L. Boyer. Feature Learning by Multidimensional Scaling and its Applications in Object Recognition. 2013 26th SIBGRAPI Conference on Graphics, Patterns and Images (Sibgrapi). IEEE, 2013. [preprint]
- Under review.
The two-stage iterated Levenberg-Marquardt algorithm (ILMA) for solving multidimensional scaling (MDS):
The raw stress vs. running time plot of the SMACOF algorithm, its variants, and the proposed iterated Levenberg-Marquardt algorithm (ILMA) on the Swiss roll geodesic distance matrix:
Flattened Swiss roll surface by applying MDS with iterated Levenberg-Marquardt algorithm on the geodesic distance matrix:
UIUC car recognition performance:
AUTHOR="Quan Wang and Kim L. Boyer",
TITLE="Feature Learning by Multidimensional Scaling and its Applications in Object Recognition",
BOOKTITLE="SIBGRAPI 2013 - Technical Papers",