Skip to search formSkip to main contentSkip to account menu
DOI:10.5573/IEIESPC.2015.4.1.035 - Corpus ID: 61016466
@article{Yoo2015DeepCN, title={Deep Convolution Neural Networks in Computer Vision: a Review}, author={Hyeon-Joong Yoo}, journal={IEIE Transactions on Smart Processing and Computing}, year={2015}, volume={4}, pages={35-43}, url={https://api.semanticscholar.org/CorpusID:61016466}}
- H. Yoo
- Published 28 February 2015
- Computer Science
- IEIE Transactions on Smart Processing and Computing
This review paper is focusing on techniques directly related to DCNNs, especially those needed to understand the architecture and techniques employed in GoogLeNet network.
119 Citations
3
56
18
Figures from this paper
- figure 1
- figure 2
- figure 3
- figure 4
- figure 5
- figure 6
- figure 7
- figure 8
Topics
ImageNet Large Scale Visual Recognition Challenge (opens in a new tab)Deep Convolutional Neural Networks (opens in a new tab)Deep Learning (opens in a new tab)Computer Vision (opens in a new tab)Architecture (opens in a new tab)Scale Invariance (opens in a new tab)Classification (opens in a new tab)Hebbian Principle (opens in a new tab)
119 Citations
- Pu HaoJun-Hai ZhaiSufang Zhang
- 2017
Computer Science
2017 International Conference on Machine Learning…
Inspired by the idea of extreme learning machine (ELM), a simple and effective method for image classification using a neural network with 6 layers to classify images is proposed.
- 5
- H. ZhaoWeichen XueXiaobo LiZhangxuan GuLi NiuLiqing Zhang
- 2020
Computer Science
IET Comput. Vis.
This study proposes an effective framework that takes the advantage of deep learning on the static image feature extraction to tackle the video data and achieves a much better performance than the existing long short-term memory-based methods and consumes far fewer resources than theexisting 3D end-to-end models.
- Jean-François CouchotR. CouturierC. GuyeuxM. Salomon
- 2016
Computer Science
ArXiv
- 52 [PDF]
- Pornntiwa PawaraEmmanuel OkaforOlarik SurintaL. SchomakerM. Wiering
- 2016
Computer Science, Environmental Science
Comparing local feature descriptors and bags of visual words with different classifiers to deep convolutional neural networks (CNNs) on three plant datasets; AgrilPlant, LeafSnap, and Folio shows that the deep CNN methods outperform the hand-crafted features.
- 95
- PDF
- Serhat Kılıçarslan
- 2022
Computer Science, Medicine
Multimedia Tools and Applications
Experimental studies and the results of the experimental studies show that the proposed HardSReLUE activation function and the YOLOv5 architecture have better performance than others.
- 3
- Pornntiwa PawaraEmmanuel OkaforOlarik SurintaLambert SchomakerM. Wiering
- 2017
Computer Science, Environmental Science
ICPRAM
This paper aims at comparing local feature descriptors and bags of visual words with different classifiers to deep convolutional neural networks (CNNs) on three plant datasets; AgrilPlant, LeafSnap, and Folio and shows that the deep CNN methods outperform the hand-crafted features.
- 1
- PDF
- Luo ShaZhiwen YuanXu KanZhang JinliHonggang Deng
- 2020
Computer Science
Journal of Physics: Conference Series
In the proposed method, DenseNet is adopted to extract both spatial and temporal features, and focal loss is employed to alleviate the influence of imbalanced data.
- 6
- PDF
- A. ZhuJing JinTian WangQiurong Zhu
- 2017
Computer Science
2017 4th IAPR Asian Conference on Pattern…
A Multi-Resolution Convolutional Neural Network (MR-CNN) is proposed to train and learn the multi-scale feature of each body part and the experimental results demonstrate the effectiveness of the proposed method.
- 3
- 2020
Computer Science
This thesis proposes a new self-supervised learning method, Multi-scale MoCo, which is based on the original MoCo but does not directly pass the image through the encoder after the augmented images, and the weights of other layers except the final linear layer are frozen without changing.
- PDF
- Tidor-Vlad Pricope
- 2021
Computer Science
ArXiv
This work extensively test an end-to-end vanilla neural network (MLP) approach in pure numpy without any pre-processing or feature extraction done beforehand, and shows that basic data mining operations can significantly improve the performance of the models in terms of computational time, without sacrificing much accuracy.
...
...
40 References
- Christian SzegedyWei Liu Andrew Rabinovich
- 2015
Computer Science
2015 IEEE Conference on Computer Vision and…
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition…
- 41,367 [PDF]
- Andrew G. Howard
- 2014
Computer Science
ICLR
This paper summarizes the entry in the Imagenet Large Scale Visual Recognition Challenge 2013, which achieved a top 5 classification error rate and achieved over a 20% relative improvement on the previous year's winner.
- 421 [PDF]
- A. KrizhevskyI. SutskeverGeoffrey E. Hinton
- 2012
Computer Science
Commun. ACM
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
- 113,058
- Highly Influential
- PDF
- P. SermanetD. EigenXiang ZhangMichaël MathieuR. FergusYann LeCun
- 2014
Computer Science
ICLR
This integrated framework for using Convolutional Networks for classification, localization and detection is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 and obtained very competitive results for the detection and classifications tasks.
- 4,912 [PDF]
- Min LinQiang ChenShuicheng Yan
- 2014
Computer Science
ICLR
With enhanced local modeling via the micro network, the proposed deep network structure NIN is able to utilize global average pooling over feature maps in the classification layer, which is easier to interpret and less prone to overfitting than traditional fully connected layers.
- 6,042 [PDF]
- Matthew D. ZeilerR. Fergus
- 2014
Computer Science
ECCV
A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.
- 15,213 [PDF]
- Matthew D. Zeiler
- 2013
Computer Science
This work introduces a new regularization method for convolutional networks called stochastic pooling which relies on sampling noise to prevent these powerful models from overfitting, and introduces a novel optimization method called ADADELTA which shows promising convergence speeds in practice whilst being robust to hyper-parameter selection.
- 55
- PDF
- L. DengDong Yu
- 2014
Computer Science, Engineering
Found. Trends Signal Process.
This monograph provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks, including natural language and text processing, information retrieval, and multimodal information processing empowered by multi-task deep learning.
- 3,452
- PDF
- P. SermanetYann LeCun
- 2011
Computer Science
The 2011 International Joint Conference on Neural…
This work applies Convolutional Networks (ConvNets) to the task of traffic sign classification as part of the GTSRB competition, and yields the 2nd-best accuracy above the human performance.
- 754
- PDF
- Ross B. GirshickJeff DonahueTrevor DarrellJ. Malik
- 2014
Computer Science
2014 IEEE Conference on Computer Vision and…
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
- 24,578 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers
Fig. 1. Hierarchical structure of the neocognitron network (Adapted from [19]).
Published in 2015
Deep Convolution Neural Networks in Computer Vision: a Review
H. Yoo
Figure 1 of 8