Sparse coding---that is, modeling data vectors as sparse linear combinations of dictionary elements---is widely used in machine learning, neuroscience, signal processing, and statistics. This talk addresses the problem of learning the dictionary, adapting it to specific data and image understanding tasks. In particular, I will present a fast on-line approach to unsupervised dictionary learning ...

The soundness of training data is important to the performance of a learning model. However in recommender systems, the training data are usually noisy, because of the randomness nature of users’ behaviors and the sparseness of the users’ feedback towards the recommendations. In this work, we would like to propose a noise elimination model to preprocess the training data in recommender systems....

Dictionary training for sparse representations involves dealing with large chunks of data and complex algorithms that determine time consuming implementations. SBO is an iterative dictionary learning algorithm based on constructing unions of orthonormal bases via singular value decomposition, that represents each data item through a single best fit orthobase. In this paper we present a GPGPU ap...

Sparse representations of images in overcomplete bases (i.e., redundant dictionaries) have many applications in computer vision and image processing. Recent works have demonstrated improvements in image representations by learning a dictionary from training data instead of using a predefined one. But learning a sparsifying dictionary can be computationally expensive in the case of a massive tra...

Traditional dictionary learning methods are based on quadratic convex loss function and thus are sensitive to outliers. In this paper, we propose a generic framework for robust dictionary learning based on concave losses. We provide results on composition of concave functions, notably regarding supergradient computations, that are key for developing generic dictionary learning algorithms applic...

In recent years, dictionaries combined with sparse learning techniques became extremely popular in computer vision. The image denoising approaches can be categorized as spatial domain, transform domain, and dictionary learning based according to the image representation. Using machine learning, sparse representations have become a trend and are used image and vision applications. The general id...

In this paper, we suggest to use a modified version of Smoothed-!0 (SL0) algorithm in the sparse representation step of iterative dictionary learning algorithms. In addition, we use a steepest descent for updating the non unit columnnorm dictionary instead of unit column-norm dictionary. Moreover, to do the dictionary learning task more blindly, we estimate the average number of active atoms in...

Abstract – Finding a basis matrix (dictionary) by which objective signals are represented sparsely is of major relevance in various scientific and technological fields. We consider a problem to learn a dictionary from a set of training signals. We employ techniques of statistical mechanics of disordered systems to evaluate the size of the training set necessary to typically succeed in the dicti...

We propose a robust multimodal dictionary learning method for multimodal images. Joint dictionary learning for both modalities may be impaired by lack of correspondence between image modalities in training data, for example due to areas of low quality in one of the modalities. Dictionaries learned with such non-corresponding data will induce uncertainty about image representation. In this paper...

Convolutional sparse representations are a form of sparse representation with a dictionary that has a structure that is equivalent to convolution with a set of linear filters. While effective algorithms have recently been developed for the convolutional sparse coding problem, the corresponding dictionary learning problem is substantially more challenging. Furthermore, although a number of diffe...