Recent advances in convolutional neural networks
Jiuxiang Gu,Zhenhua Wang,Jason Kuen,Lianyang Ma,Amir Shahroudy,Bing Shuai,Ting Liu,Xingxing Wang,Gang Wang,Jianfei Cai,Tsuhan Chen +10 more
TLDR
A broad survey of the recent advances in convolutional neural networks can be found in this article, where the authors discuss the improvements of CNN on different aspects, namely, layer design, activation function, loss function, regularization, optimization and fast computation.About:
This article is published in Pattern Recognition.The article was published on 2018-05-01 and is currently open access. It has received 3125 citations till now. The article focuses on the topics: Deep learning & Convolutional neural network.read more
Citations
More filters
Journal ArticleDOI
Dilated Dense U-Net for Infant Hippocampus Subfield Segmentation
Hancan Zhu,Feng Shi,Li Wang,Sheng-Che Hung,Meng Hsiang Chen,Shuai Wang,Weili Lin,Dinggang Shen,Dinggang Shen +8 more
TL;DR: A new fully convolutional network (FCN) is proposed for infant hippocampal subfield segmentation by embedding the dilated dense network in the U-net, namely DUnet, which can generate multi-scale features while keeping high spatial resolution.
Journal ArticleDOI
Deep Learning for Classification of the Chemical Composition of Particle Defects on Semiconductor Wafers
TL;DR: In this article, a deep convolutional neural network (CNN) was proposed for defect classification based on a combination of scanning electron microscopy (SEM) images and energy-dispersive x-ray (EDX) spectroscopy data.
Journal ArticleDOI
Convolutional neural networks based on multi-scale additive merging layers for visual smoke recognition
TL;DR: A basic block of convolutional neural networks and stack basic blocks are designed to propose a novel deep multi-scale CNN (DMCNN) for smoke recognition, an efficient, lightweight CNN model with about 1 M parameters that are far less than other CNN methods.
Journal ArticleDOI
Robust occlusion-aware part-based visual tracking with object scale adaptation
TL;DR: An occlusion-aware part-based tracker for robust visual tracking is proposed that achieves outstanding performance against the state-of-the-art methods and greatly alleviates the error accumulation of the incorrect information and efficiently achieves long-term tracking.
Journal ArticleDOI
Ensemble Convolutional Neural Networks for Mode Inference in Smartphone Travel Survey
TL;DR: In this paper, the authors developed ensemble convolutional neural networks (CNNs) to classify the transportation mode of trip data collected as part of a large-scale smartphone travel survey in Montreal, Canada.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.