Learning image representations from the pixel level via hierarchical sparse coding

By Kai Yu, Yuanqing Lin, John D. Lafferty. 2011

242 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Learning: Methods and Applications (2014, methodology): “In addition to unsupervised pretraining using greedy layer-wise procedures [28, 164, 295], the supervised pretraining, or sometimes called discriminative pretraining, has also been shown to be effective [28, 161, 324, 432] and in cases where labeled training data are abundant performs better than th”
3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks (2014, methodology): “This is a procedure widely applied to obtain deformation and shift invariance [11, 38].”
Learning Invariant Representations with Local Transformations (2012, background): “In fact, recent literature (Yu et al., 2011; Lee et al., 2011; Vincent et al., 2008) suggests that some level of invariance to local transformations (e.g., few pixel translation or coordinate-wise noise) leads to improved performance in classiﬁcation.”
Deep Learning of Representations: Looking Forward (2013, background): “ny zeros) in the MAP posterior. Sparse coding is not actually very good as a generative model, but has been very successful for unsupervised feature learning (Raina et al., 2007; Coates and Ng, 2011; Yu et al., 2011; Grosse et al., 2007; Jenatton et al., 2009; Bach et al., 2011). See Bengio et al. (”
Unsupervised Template Learning for Fine-Grained Object Recognition (2012, background): “Over the last decades, computer vision researchers have done a lot of work in designing effective and efficient patch-level features for object recognition [16, 17, 18, 19, 20, 21, 22].”
Unsupervised Feature Learning for RGB-D Based Object Recognition (2012, methodology): “hierarchical sparse coding [39], and hierarchical matching pursuit [7] have been proposed to this end.”
DASH-N: Joint Hierarchical Domain Adaptation and Feature Learning (2015, background): “Motivated by recent works on deep learning, multi-layer sparse coding networks [33], [36], [37] have been proposed to build feature hierarchies layer by layer using sparse codes and spatial pooling.”
A Deep Structured Model with Radius–Margin Bound for 3D Human Activity Recognition (2015, methodology): “After each 3D convolution, the max-pooling operation is introduced to enhance the deformation and shift invariance [20, 52].”
Multipath Sparse Coding Using Hierarchical Matching Pursuit (2013, background): “A variety of learning and coding techniques have been proposed and evaluated, such as deep belief nets [12], deep autoencoders [17], deep convolutional neural networks [15], and hierarchical sparse coding [32, 3].”
Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives (2012, background): “…as a feature representation scheme, including natural image modeling (Raina et al. , 2007; Kavukcuoglu et al. , 2008; Coates and Ng, 2011a; Yu et al. , 2011), audio classiﬁcation (Grosse et al. , 2007), natural language processing (Bagnell and Bradley, 2009), as well as being a very…”
Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery (2012, unknown): “While Yu et al. (2011) and Zeiler et al. (2009) have recently shown some success at learning hierarchical sparse coding, our goal is to integrate the feature extraction scheme into a proven generative model framework such as the deep Boltzmann Machine (Salakhutdinov and Hinton, 2009).”
Representation Learning: A Review and New Perspectives (2012, background): “…as a feature representation scheme, including natural image modeling (Raina et al., 2007; Kavukcuoglu et al., 2008; Coates and Ng, 2011a; Yu et al., 2011), audio classification (Grosse et al., 2007), NLP (Bagnell and Bradley, 2009), as well as being a very successful model of the early…”
Sparse coding based visual tracking: Review and experimental comparison (2013, background): “In addition, motivated by the success of deep learning in object recognition, hierarchical sparse coding [68] should also be investigated in visual tracking.”
Large-Margin Multi-Modal Deep Learning for RGB-D Object Recognition (2015, background): “[4], hierarchical sparse coding [50] and local coordinate coding”
Bootstrapping bilinear models of Simple Vehicles (2015, methodology): “Extensions using three-way interactions have been used to represent motions and transformations at the pixel level (Memisevic and Hinton, 2007; Memisevic and Hinton, 2010; Ranzato and Hinton, 2010; Larochelle and Hinton, 2010; Yu, Lin, and Lafferty, 2011; Hutchinson, Deng, and Yu, 2013).”