Multipath Sparse Coding Using Hierarchical Matching Pursuit

By Liefeng Bo, Xiaofeng Ren, Dieter Fox. 2013

212 citations recorded by the source corpus.

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

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

In Representation & Self-Supervised Learning

In Signal Processing

Citations in the corpus

Visualizing and Understanding Convolutional Networks (2013, methodology): “Our ImageNet-pretrained model beats the current state-of-the-art results obtained by Bo et al. (Bo et al., 2013) by a signiﬁcant margin: 74.2% vs 55.2% for 60 training images/class.”
Discriminative Unsupervised Feature Learning with Convolutional Neural Networks (2014, neutral): “This is not surprising, since Caltech-101 images are often well aligned, and this dataset bias makes spatial invariance less useful.”
Scattering Networks for Hybrid Representation Learning (2018, background): “However, several works indicate that this is not a generic enough representation on top of which to build further modules [6], [31].”
Deep roto-translation scattering for object classification (2014, methodology): “State-of-the-art unsupervised classification results for Caltech, without data augmentation, are obtained with a Multipath-SC algorithm [2], which has 3 unsupervised encoding layers.”
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks (2015, neutral): “[5].”
Scaling the Scattering Transform: Deep Hybrid Networks (2017, neutral): “However, several works indicate that this is not a generic enough representation to build further modules on top of [21, 2].”
SemiContour: A Semi-supervised Learning Approach for Contour Detection (2016, unknown): “(7) for better sparse reconstruction [5].”
Sparse Modeling for Image and Vision Processing (2014, methodology): “Later, this idea was also found useful in other classification schemes [Bo et al., 2013].”
Unsupervised feature learning for 3D scene labeling (2014, background): “learning communities ([26], [27], [23], [15]).”
DASH-N: Joint Hierarchical Domain Adaptation and Feature Learning (2015, background): “If f is a vector corresponding to a patch, then the contrast-normalization can be performed as in [37] ˆ f = f f 2 + , (5) where is some parameter.”
Unsupervised Learning of Discriminative Attributes and Visual Representations (2016, background): “Many unsupervised studies [4, 5, 6, 24, 53] focus on learning generic visual features by modeling the data distribution (e.”
Learning hierarchical sparse features for RGB-(D) object recognition (2014, methodology): “The features from different layers encode different amounts of spatial invariance (mainly due to spatial pooling and contrast normalization), so additional layers could boost the accuracy further, as shown in Bo et al. (2013).”
Learning by Stretching Deep Networks (2014, background): “Recent results have shown that using one or more layers of these feature learning algorithms is sufﬁ-cient to obtain state of the art results for many object recognition tasks (Bo et al., 2012; Coates et al., 2011).”
A Deep Generative Deconvolutional Image Model (2015, unknown): “8 Mu-SC (Bo et al., 2013) 42.”
Hierarchical Convolutional Deep Learning in Computer Vision (2013, methodology): “Within each block, we show a randomly chosen subset of features at epochs [1,2,5,10,20,30,40,64].”
Building Efficient Deep Hebbian Networks for Image Classification Tasks (2017, unknown): “However, the combined model (DPM+Gist+SPM) [13] and the Multipath-HMP (MHMP) [4] still outperform the DHN.”
Modeling Image Patches with a Generic Dictionary of Mini-epitomes (2014, unknown): “41 M-HMP [2] 82.”
Author manuscript, published in "International Journal of Computer Vision (2013)" International Journal of Computer Vision manuscript No. (will be inserted by the editor) Image Classification with the Fisher Vector: Theory and Practice (2013, unknown): “Wang et al (2010 2012) makes use of color information.”
Learning to Track at 100 FPS with Deep Regression Networks (2016, background): “In many other areas of computer vision, such as image classification, object detection, segmentation, or activity recognition, machine learning has allowed vision algorithms to train from offline data and learn about the world [5,23,13,25,9,28].”