Feature Learning by Multidimensional Scaling and its Applications in Object Recognition
This work addresses the challenge of extracting rich semantic information from images for object recognition, though it appears incremental as it builds on existing distance metrics like SPM.
The paper tackles the problem of learning semantic image features for object recognition by applying multidimensional scaling (MDS) to pairwise image distances, resulting in MDS features that achieve exceptional performance on the UIUC car dataset.
We present the MDS feature learning framework, in which multidimensional scaling (MDS) is applied on high-level pairwise image distances to learn fixed-length vector representations of images. The aspects of the images that are captured by the learned features, which we call MDS features, completely depend on what kind of image distance measurement is employed. With properly selected semantics-sensitive image distances, the MDS features provide rich semantic information about the images that is not captured by other feature extraction techniques. 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.