Publications

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication


Year(s) from:  to 
Author:
Keywords (separated by spaces):

Unsupervised High-level Feature Learning by Ensemble Projection for Semi-supervised Image Classification and Image Clustering

D. Dai and L. Van Gool
, 2015
Computer Vision Lab, ETH Zuerich

Abstract

This paper investigates the problem of semi-supervised image classification and image clustering. Unlike pre- vious methods to develop sophisticated classifier models, our method learns a new image representation from all available data (labeled and unlabeled) by exploiting the patterns of data distribution in a novel manner. Particularly, a rich set of visual prototypes are sampled from all available data, and are taken as surrogate classes to train discriminative classifiers; images are projected (classified) via the classifiers and the projected values (similarities to the prototypes) are stacked to build a feature vector. The training set is noisy. Hence, in the spirit of ensemble learning we create a set of such training sets which are all diverse, leading to di- verse classifiers. The method is dubbed Ensemble Projection (EP). EP captures not only the characteristics of indi- vidual images, but also the relationships among images. It is conceptually simple and computationally efficient, yet ef- fective and flexible. Experiments on eight standard datasets show that: (1) EP outperforms previous methods for semi- supervised image classification; (2) EP produces promising results for self-taught image classification, where unlabeled samples are a random collection of images rather than being from the same distribution as the labeled ones; and (3) EP improves over the original features for image clustering. The code of the method is available at www.vision.ee. ethz.ch/ ̃daid/EnProDeepFets.


Download in pdf format
@Techreport{eth_biwi_01215,
  author = {D. Dai and L. Van Gool},
  title = {Unsupervised High-level Feature Learning by Ensemble Projection for Semi-supervised Image Classification and Image Clustering},
  year = {2015},
  month = {May},
  institution = {Computer Vision Lab, ETH Zuerich},
  keywords = {}
}