Supervised translation-invariant sparse coding

By Jianchao Yang, Kai Yu, Thomas S. Huang. 2010

379 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Understanding Image Representations by Measuring Their Equivariance and Equivalence (2014, background): “2004; Sivic andZisserman 2003), sparse (Yang et al. 2010) and local coding (Wang et al.”
Visualizing Deep Convolutional Neural Networks Using Natural Pre-images (2015, background): “2004; Sivic and Zisserman 2003), sparse (Yang et al. 2010) and local coding (Wang et al.”
Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification (2016, background): “Yang et al. (2010) extended this supervised sparse coding with max-pooling to obtain translation-invariant local features.”
Efficient Algorithms for Convolutional Sparse Representations (2016, background): “The most frequent application area within this stream has been image classiﬁcation [11], [12], [14], [15], [17] and detection [11], [16] tasks, but segmentation in biological imagery has also been considered [19], and image denoising has received very brief attention [14].”
LRBM: A Restricted Boltzmann Machine Based Approach for Representation Learning on Linked Data (2014, methodology): “SSC and ICA have worse performance on SocialE while achieve relatively better performance on Robot.”
Image classification by non-negative sparse coding, low-rank and sparse decomposition (2011, methodology): “Linear SVM classifier is then used to predict the category of images due to its advantages in speed and good performance for the sparse coding parameters [4, 11, 16, 28].”
Top-down visual saliency via joint CRF and dictionary learning (2012, methodology): “Unlike [28] that uses max pooling to resolve geometric ambiguity, we use CRF to regulate the patches within their local contexts for learning salient visual words in complex scenes.”
Sparse Modeling for Image and Vision Processing (2014, methodology): “…leading to state-of-the-art results for image inpainting and demosaicking [Mairal et al., 2008c, 2009], super-resolution and deblurring [Yang et al., 2010a, 2012a, Couzinie-Devy et al., 2011, Dong et al., 2011b, Zeyde et al., 2012, Wang et al., 2012], face compression [Bryt and Elad,…”
Fisher Discrimination Dictionary Learning for sparse representation (2011, methodology): “Recently sparse representation techniques have also led to promising results in image classification, e.g. face recognition (FR) [5] [6] [7] [10] [31], digit and texture classification [8] [9] [11] [12], etc.”
Toward a Practical Face Recognition System: Robust Alignment and Illumination by Sparse Representation (2012, background): “With the same training and testing sets, [35] is able to handle the remaining misalignment and achieves state-of-the-art performance on the CMU Multi-PIE database.”
Building a better probabilistic model of images by factorization (2011, background): “In particular, sparse coding models have been shown to yield features that match the properties of neurons in the visual cortex and also yield improved performance at image analysis and classification tasks [38, 1, 39, 16, 30, 19, 18, 28, 26].”
The devil is in the details: an evaluation of recent feature encoding methods (2011, background): “Papers have flourished [17, 23, 24, 25, 27], and some have reported very good results on challenging benchmarks such as the PASCAL VOC classification challenge [5].”