Are sparse representations really relevant for image classification?

By Roberto Rigamonti, Matthew A. Brown, Vincent Lepetit. 2011

221 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Sparse coding based visual tracking: Review and experimental comparison (2013, background): “…methods are motivated by face recognition work, there are some researchers claimed that face recognition may be not a sparse representation problem [62,63] and their experimental results on face recognition indicated that non-sparse representation based on ‘ 2 norm minimization (e.g., 22 ) is more…”
Sparse Modeling for Image and Vision Processing (2014, methodology): “A variant of the convolutional sparse coding model has also been investigated by Rigamonti et al. [2013], where the dictionary elements are spatially separable, or partially separable.”
Unsupervised Feature Learning for Aerial Scene Classification (2014, methodology): “Previously, in [26], [27] a similar soft threshold activation function was used to estimate sparse codes.”
Beyond spatial pyramids: Receptive field learning for pooled image features (2012, background): “Recent papers [6, 28, 9] have explored the relationship between dictionary learning and encoding, and have proposed simple yet effective approaches that achieve competitive results.”
Nuclear Norm Based Matrix Regression with Applications to Face Recognition with Occlusion and Illumination Changes (2014, background): “The model shows the strong ability of dealing with sparse random pixel corruption and block occlusion.”
Learning Semantic Image Representations at a Large Scale (2014, background): “Recent papers [19, 93, 20] have explored the relationship between dictionary learning and encoding, and have proposed simple yet effective approaches that achieve competitive results.”
Hierarchical Convolutional Deep Learning in Computer Vision (2013, background): “It has previously been shown that sparsity encourages learning of distinctive features, however it is not necessarily useful for classification [103].”