Joint Dictionary and Classifier learning for Categorization of Images using a Max-margin Framework

Joint Dictionary and Classifier learning for Categorization of Images using a Max-margin Framework. Lobel, H., Vidal, R., Mery, D., & Soto., A. In 6th Pacific-Rim Symposium on Image and Video Technology, PSIVT, 2013.

Paper abstract bibtex 7 downloads

The Bag-of-Visual-Words (BoVW) model is a popular approach for visual recognition. Used successfully in many different tasks, simplicity and good performance are the main reasons for its popularity. The central aspect of this model, the visual dictionary, is used to build mid-level representations based on low level image descriptors. Classifiers are then trained using these mid-level representations to perform categorization. While most works based on BoVW models have been focused on learning a suitable dictionary or on proposing a suitable pooling strategy, little effort has been devoted to explore and improve the coupling between the dictionary and the top-level classifiers, in order to gen- erate more discriminative models. This problem can be highly complex due to the large dictionary size usually needed by these methods. Also, most BoVW based systems usually perform multiclass categorization using a one-vs-all strat- egy, ignoring relevant correlations among classes. To tackle the previous issues, we propose a novel approach that jointly learns dictionary words and a proper top- level multiclass classifier. We use a max-margin learning framework to minimize a regularized energy formulation, allowing us to propagate labeled information to guide the commonly unsupervised dictionary learning process. As a result we produce a dictionary that is more compact and discriminative. We test our method on several popular datasets, where we demonstrate that our joint optimization strategy induces a word sharing behavior among the target classes, being able to achieve state-of-the-art performance using far less visual words than previous approaches.

@InProceedings{	  lobel-b:etal:2013,
  author	= {H. Lobel and R. Vidal and D. Mery and A. Soto.},
  title		= {Joint Dictionary and Classifier learning for
		  Categorization of Images using a Max-margin Framework},
  booktitle	= {6th Pacific-Rim Symposium on Image and Video Technology,
		  PSIVT},
  year		= {2013},
  abstract	= {The Bag-of-Visual-Words (BoVW) model is a popular approach
		  for visual recognition. Used successfully in many different
		  tasks, simplicity and good performance are the main reasons
		  for its popularity. The central aspect of this model, the
		  visual dictionary, is used to build mid-level
		  representations based on low level image descriptors.
		  Classifiers are then trained using these mid-level
		  representations to perform categorization. While most works
		  based on BoVW models have been focused on learning a
		  suitable dictionary or on proposing a suitable pooling
		  strategy, little effort has been devoted to explore and
		  improve the coupling between the dictionary and the
		  top-level classifiers, in order to gen- erate more
		  discriminative models. This problem can be highly complex
		  due to the large dictionary size usually needed by these
		  methods. Also, most BoVW based systems usually perform
		  multiclass categorization using a one-vs-all strat- egy,
		  ignoring relevant correlations among classes. To tackle the
		  previous issues, we propose a novel approach that jointly
		  learns dictionary words and a proper top- level multiclass
		  classifier. We use a max-margin learning framework to
		  minimize a regularized energy formulation, allowing us to
		  propagate labeled information to guide the commonly
		  unsupervised dictionary learning process. As a result we
		  produce a dictionary that is more compact and
		  discriminative. We test our method on several popular
		  datasets, where we demonstrate that our joint optimization
		  strategy induces a word sharing behavior among the target
		  classes, being able to achieve state-of-the-art performance
		  using far less visual words than previous approaches. },
  url		= {http://saturno.ing.puc.cl/media/papers_alvaro/Hans-PSIVT-13.pdf}
}

Downloads: 7