Convolutional networks and applications in vision

By Yann LeCun, Koray Kavukcuoglu, Clément Farabet. 2010

2,129 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Semi-Supervised Sequence Modeling with Cross-View Training (2018, background): “Early approaches to deep semi-supervised learning pre-train neural models on unlabeled data, which has been successful for applications in computer vision (Jarrett et al., 2009; LeCun et al., 2010) and NLP.”
Scattering Networks for Hybrid Representation Learning (2018, background): “These architectures are designed as very deep cascades of non-linear end-to-end learnedmodules [32].”
Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning (2016, background): “Stochastic gradient descent, dropout [8], randomized data transformation and augmentation [9] and many other training techniques that are essential for fast convergence and effective generalization of the learning functions introduce some non-deterministic behavior to the learning system.”
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning (2017, background): “Deep learning models perform extremely well with correlated data, which contributed to substantial improvements in computer vision [45], image processing, video processing, face recognition [80], speech recognition [33], text-to-speech systems [62] and natural language processing [2, 14, 88].”
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks (2015, background): “However, these same architectures have been shown to be unstable to small, well sought, perturbations of the images.”
Geometric Deep Learning: Going beyond Euclidean data (2016, background): “and computer vision [5], [6], [7], [8], [9], [10], [11] (the reader is referred to [12], [13] for many additional examples of successful applications of deep learning).”
Qualitatively characterizing neural network optimization problems (2014, methodology): “convolutional networks (LeCun et al., 2010), unsupervised models, recurrent models of sequences, and analytically tractable factored linear models.”
Deep roto-translation scattering for object classification (2014, background): “A convolutional network is a multilayer architecture, which cascades spatial convolutions and pooling operators, which includes sub-samplings [13].”
Group Invariant Scattering (2011, background): “Scattering operators are extended on L2(G), where G is a compact Lie group, and are invariant under the action of G. Combining a scattering on L2(Rd) and on L 2(SO(d)) defines a translation and rotation invariant scattering on L 2(Rd).”
Scaling the Scattering Transform: Deep Hybrid Networks (2017, neutral): “These architectures are designed as very deep cascades of non-linear end-to-end learned modules [22].”
Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review (2016, background): “automatically learn multilevel hierarchies of features that are invariant to irrelevant variations of samples while preserving relevant information [150], [151], and has achieved great success on image classification and scene labeling [152], [153].”
Class-Incremental Learning: A Survey (2023, background): “Hence, ideal CIL algorithms should work for any type of backbones, e.g. , multi-layer perceptron (MLP) [30], convolutional neural network (CNN) [31], and Vision Transformer (ViT) [19].”
Breast cancer detection using deep convolutional neural networks and support vector machines (2019, methodology): “A convolutional neural network (CNN) consists of multiple trainable stages stacked on top of each other, followed by a supervised classifier and sets of arrays named feature maps ( LeCun, Kavukcuoglu & Farabet, 2010 ).”
Deep learning for plant identification using vein morphological patterns (2016, background): “For a more detailed description of this kind of models we refer the reader to [24] and the references therein.”
Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life (2016, methodology): “In this paper we treat RUL estimation problem as multivariate time series regression and solve it by adapting one particular deep learning model, namely Convolutional Neural Network (CNN) adapted from deep learning model for image classification [1,12,13], which is the first attempt to leverage deep”
ShiDianNao: Shifting vision processing closer to the sensor (2015, neutral): “Yet, for now, the figure should give the reader a sufficient broad idea of the mapping to follow the development of the architecture in the next section.”
Convolutional adaptive denoising autoencoders for hierarchical feature extraction (2018, background): “1 Typical CNN structure with seven layers [17] (C1 is the first convolutional layer with N1 feature maps, and S2 is the first subsampling layer)”