In this work, we investigate how to automatically reassign the manually annotated labels at the image-level to those contextually derived semantic regions. First, we propose a bi-layer sparse coding formulation for uncovering how an image or semantic region can be robustly reconstructed from the over-segmented image patches of an image set. We then harness it for the automatic label to region a...

In high dimensional data sets not all dimensions contain an equal amount of information and most of the time global features are more important than local differences. This makes it difficult to select a similarity measures that inherently considers these differences in weighting. We are presenting a sparse coding based similarity measure that is capable of extracting and emphasizing relevant e...

We present a system for musical genre classification based on audio features extracted from signals which correspond to distinct musical instrument sources. For the separation of the musical sources, we propose an innovative technique in which the convolutive sparse coding algorithm is applied to several portions of the audio signal. The system is evaluated and its performance is assessed.

Typical image classification pipeline for shallow architecture can be summarized by the following three main steps: i) a projection in high dimensional space of local features, ii) sparse constraints for the encoding scheme and iii) a pooling operation to obtain a global representation invariant to common transformation. Sparse Coding (SC) framework is one particular example of this general app...

Bottleneck autoencoders have been actively researched as a solution to image compression tasks. However, we observed that bottleneck autoencoders produce subjectively low quality reconstructed images. In this work, we explore the ability of sparse coding to improve reconstructed image quality for the same degree of compression. We observe that sparse image compression produces visually superior...

Sensory representations are not only sparse, but often overcomplete: coding units significantly outnumber the input units. For models of neural coding this overcompleteness poses a computational challenge for shaping the signal processing channels as well as for using the large and sparse representations in an efficient way. We argue that higher level overcompleteness becomes computationally tr...

This technical report presents a study of methods for learning sparse codes and localized features from data. In the context of this study, we propose a new prior for generating sparse image codes with low-energy, localized features. The experiments show that with this prior, it is possible to encode the model with significantly fewer bits without affecting accuracy. The report also introduces ...

Sparse representation has become very popular in fields of signal processing, image processing computer vision and pattern recognition. Sparse representation also has good reputation in both theoretical and practical applications. Images can be sparsely coded by structural primitives and recently the sparse coding or sparse representation has been widely used to resolve the problems in image re...

In this paper, we proposed a novel sparse coding algorithm by using the class labels to constrain the learning of codebook and sparse code. We not only use the class label to train the classifier, but also use it to construct class conditional codewords to make the sparse code as discriminative as possible. We first construct ideal sparse codes with regarding to the class conditional codewords,...