Deep Epitomic Convolutional Neural Networks
Explore this paper's citation graph
Summary
This paper proposes the epitomic convolution as a new building block for deep neural networks and shows that error back-propagation can successfully learn multiple epitomic layers in a supervised fashion.
- Type
- preprint
- Published
- 2014-06-10
- Cited by
- 7
- References
- 30
- Access
- Open access
- OpenAlex
- https://openalex.org/W70846133
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:18815368
Keywords
MNIST database, Convolutional neural network, Pooling, Computer science, Artificial intelligence
References
- Return of the Devil in the Details: Delving Deep into Convolutional Nets
- Modeling Image Patches with a Generic Dictionary of Mini-Epitomes
- Sparse and Redundant Modeling of Image Content Using an Image-Signature-Dictionary
- CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Building high-level features using large scale unsupervised learning
- Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
- Epitomic analysis of appearance and shape
- Learning invariant features through topographic filter maps
- Topographic Product Models Applied to Natural Scene Statistics
- Hierarchical models of object recognition in cortex
- Distinctive Image Features from Scale-Invariant Keypoints
- LIBSVM: A library for support vector machines
- Joint Deep Learning for Pedestrian Detection
- ImageNet classification with deep convolutional neural networks
- Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories
- Distinctive Image Features from Scale-Invariant Keypoints Abstract by Matthijs Dorst Based on the paper by
- Deconvolutional networks
Cited by
- Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection
- Modeling local and global deformations in Deep Learning: Epitomic convolution, Multiple Instance Learning, and sliding window detection
- ImageNet Large Scale Visual Recognition Challenge
- Good Practice in CNN Feature Transfer
- Efficient learning of local image descriptors
- Efficient Convolutional Network Learning Using Parametric Log Based Dual-Tree Wavelet ScatterNet
- AHCNet: An Application of Attention Mechanism and Hybrid Connection for Liver Tumor Segmentation in CT Volumes
Related papers
- Max-min convolutional neural networks for image classification
- Deep Convolutional Neural Network with Dilated Convolution Using Small Size Dataset
- Convolutional Neural Network (CNN) for Image Detection and Recognition
- Shallow convolutional neural network for image classification
- Very deep convolutional neural network based image classification using small training sample size
- Human Activity Recognition Using 2D Convolutional Neural Networks
- Classification of fashion article images using convolutional neural networks