MoTIF: An Efficient Algorithm for Learning Translation Invariant Dictionaries

Jost, P.; Vandergheynst, Pierre; Lesage, Sylvain; Gribonval, Rémi

doi:10.1109/icassp.2006.1661411

Cited by 42 publications

(52 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Now turning back to the open problem presented in Section 1, our conjecture is that for a certain class of images, in order to obtain ideal restoration result with (P * ) , we should take a dictionary D which gives sparse representation for the collection containing all the curvatures of image in that class. We mention that the method of [13] might be useful for this task.…”

Section: Discussionmentioning

confidence: 99%

Incorporating known features into a total variation dictionary model for source separation

Zeng

2008

2008 15th IEEE International Conference on Image Processing

View full text Add to dashboard Cite

The goal of this paper is to investigate the impact of dictionary choosing for a total variation dictionary model. After theoretical analysis, we present the experiments in which the dictionary contains the curvatures of known forms (letters). The data-fidelity term of this model allows the appearance in the residue of all structures except forms being used to build the dictionary. Therefore, these forms will remain in the result image while the other structures will disappear. Our experiments are carried on the source separation problem and confirm this impression. The starting image contains letters (known) on a very structured background (an image). We show that it is possible, with this model, to obtain a reasonable separation of these structures. Finally, this work illustrates clearly that the dictionary must contain the curvature of elements which we seek to preserve.

show abstract

Section: Discussionmentioning

confidence: 99%

Incorporating known features into a total variation dictionary model for source separation

Zeng

2008

2008 15th IEEE International Conference on Image Processing

View full text Add to dashboard Cite

show abstract

“…Therefore, the learning of dictionaries in a way that is invariant to the geometric transformations of available training data is critical in a variety of practical scenarios. Transformation-invariance in dictionary learning has been addressed in several previous works, which however only target invariance to specific geometric transformations; e.g., translations [6], [7], scale changes [8], [9], or rotations and scalings [10].…”

Section: Introductionmentioning

confidence: 99%

Transformation-invariant dictionary learning for classification with 1-Sparse representations

Yüzügüler

Vural

Frossard

2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Sparse representations of images in well-designed dictionaries can be used for effective classification. Meanwhile, training data available in most realistic settings are likely to be exposed to geometric transformations, which poses a challenge for the design of good dictionaries. In this work, we study the problem of learning class-representative dictionaries from geometrically transformed image sets. In order to efficiently take account of arbitrary geometric transformations in the learning, we adopt a representation of the dictionaries in an analytic basis. Then, the proposed algorithm learns atoms that are attracted to the samples of their own class while being repelled from the samples of other classes so that the discrimination between different classes is promoted. The dictionary learning objective is formulated such that it enhances the class-discrimination capabilities of individual atoms rather than the ones of the subspaces they generate, which renders the designed dictionaries especially suitable for fast classification of query images with very sparse approximations. Experimental results demonstrate the performance of the proposed method in handwritten digit recognition applications.

show abstract

“…In these cases, one typically would want to learn a good dictionary from training data. Successful algorithms to learn dictionaries of basis functions have been proposed in the last years and applied to diverse classes of signal, including audio data [27]- [29], natural images [29]- [33] and video sequences [34]. In the next section, we propose a learning strategy adapted to synchronous multimodal signals.…”

Section: B Synchrony and Shift Invariance In Multimodal Signalsmentioning

confidence: 99%

“…We will design a novel learning algorithm that captures the underlying structures of multimodal signals overcoming both of these difficulties. We propose to learn synchronous multimodal generating functions as introduced in the previous section using a generalization of the MoTIF algorithm [29]. In [29], the authors propose a method to learn generating functions successively.…”

Section: Learning Multimodal Dictionariesmentioning

confidence: 99%

Learning Multimodal Dictionaries

Monaci

Jost

Vandergheynst

et al. 2007

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Abstract-Real-world phenomena involve complex interactions between multiple signal modalities. As a consequence, humans are used to integrate at each instant perceptions from all their senses in order to enrich their understanding of the surrounding world. This paradigm can be also extremely useful in many signal processing and computer vision problems involving mutually related signals. The simultaneous processing of multimodal data can, in fact, reveal information that is otherwise hidden when considering the signals independently. However, in natural multimodal signals, the statistical dependencies between modalities are in general not obvious. Learning fundamental multimodal patterns could offer deep insight into the structure of such signals. In this paper, we present a novel model of multimodal signals based on their sparse decomposition over a dictionary of multimodal structures. An algorithm for iteratively learning multimodal generating functions that can be shifted at all positions in the signal is proposed, as well. The learning is defined in such a way that it can be accomplished by iteratively solving a generalized eigenvector problem, which makes the algorithm fast, flexible, and free of user-defined parameters. The proposed algorithm is applied to audiovisual sequences and it is able to discover underlying structures in the data. The detection of such audio-video patterns in audiovisual clips allows to effectively localize the sound source on the video in presence of substantial acoustic and visual distractors, outperforming state-of-the-art audiovisual localization algorithms.

show abstract

MoTIF: An Efficient Algorithm for Learning Translation Invariant Dictionaries

Cited by 42 publications

References 8 publications

Incorporating known features into a total variation dictionary model for source separation

Incorporating known features into a total variation dictionary model for source separation

Transformation-invariant dictionary learning for classification with 1-Sparse representations

Learning Multimodal Dictionaries

Contact Info

Product

Resources

About