Metric Imitation by manifold transfer for efficient vision applications

— 'read' cheap features in a better way via mimicking expensive features

— Weakly Supervised Metric Learning

— CNN features teach LBP and GIST

Dengxin Dai , Till Kroeger , Radu Timofte , and Luc Van Gool


Metric learning has proven very successful. However, human annotations are necessary. In this paper, we propose an unsupervised method, dubbed Metric Imitation (MI), where metrics over cheap features (target features, TFs) are learned by imitating the standard metrics over more sophisticated, off-the-shelf features (source features, SFs) by transferring view-independent property manifold structures. In particular, MI consists of: 1) quantifying the properties of source metrics as manifold geometry, 2) transferring the manifold from source domain to target domain, and 3) learning a mapping of TFs so that the manifold is approximated as well as possible in the mapped feature domain. MI is useful in at least two scenarios where: 1) TFs are more efficient computationally and in terms of memory than SFs; and 2) SFs contain privileged information, but are not available during testing. For the former, MI is evaluated on image clustering, category-based image retrieval, and instance-based object retrieval, with three SFs and three TFs. For the latter, MI is tested on the task of example-based image super-resolution, where high-resolution patches are taken as SFs and low-resolution patches as TFs. Experiments show that MI is able to provide good metrics while avoiding expensive data labeling efforts and that it achieves state-of-the-art performance for image super-resolution. In addition, manifold transfer is an interesting direction of transfer learning.


clustering results
retrieval results
retrieval results
computational time
super-resolution results


The code and data (computed features) of Metric Imitation for the tasks of image clustering and image retrieval are available.

The code of the features (lbp, gist, phog) I used.

Dengxin Dai, Till Kroeger, Radu Timofte, and Luc Van Gool.. Metric Imitation by manifold transfer for efficient vision applications. In CVPR 2015.

This page has been edited by Dengxin Dai. All rights reserved.

web counter