Recent advances in convolutional neural networks

@article{Gu2018RecentAI,
  title={Recent advances in convolutional neural networks},
  author={Jiuxiang Gu and Zhenhua Wang and Jason Kuen and Lianyang Ma and Amir Shahroudy and Bing Shuai and Ting Liu and Xingxing Wang and Gang Wang and Jianfei Cai and Tsuhan Chen},
  journal={Pattern Recognit.},
  year={2018},
  volume={77},
  pages={354-377}
}
In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing. Among different types of deep neural networks, convolutional neural networks have been most extensively studied. Leveraging on the rapid growth in the amount of the annotated data and the great improvements in the strengths of graphics processor units, the research on convolutional neural networks has been emerged swiftly… Expand
Applications of Convolutional Neural Networks
TLDR
This paper delineates how CNN is used in computer vision, mainly in face recognition, scene labelling, image classification, action recognition, human pose estimation and document analysis, and why CNN is better than other methods. Expand
Parallel Convolutional Neural Networks for Object Detection
  • Adedeji Olugboja, Zenghui Wang, Yanxia Sun
  • Journal of Advances in Information Technology
  • 2021
In recent years, Convolutional Neural Network (CNN) has been widely applied in speech/image/video recognition and classification. Although the results achieved are so impressive, CNN architecture isExpand
Some Insights Into Convolutional Neural Networks
TLDR
Insight is provided into convolutional neural networks in three aspects: activation function, convolution operation, pooling operation, and the training of CNNs. Expand
A survey of the recent architectures of deep convolutional neural networks
TLDR
This survey focuses on the intrinsic taxonomy present in the recently reported deep CNN architectures and classifies the recent innovations in CNN architectures into seven different categories, based on spatial exploitation, depth, multi-path, width, feature-map exploitation, channel boosting, and attention. Expand
The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches
TLDR
This report presents a brief survey on development of DL approaches, including Deep Neural Network (DNN), Convolutional neural network (CNN), Recurrent Neural network (RNN) including Long Short Term Memory (LSTM) and Gated Recurrent Units (GRU), Auto-Encoder (AE), Deep Belief Network (DBN), Generative Adversarial Network (GAN), and Deep Reinforcement Learning (DRL). Expand
Performance Comparison of CNN Models Using Gradient Flow Analysis
  • S. Noh
  • Computer Science
  • Informatics
  • 2021
TLDR
The gradient flows of the VGGNet, ResNet, SENet, and DenseNet models were analyzed and compared, and the reasons for the differences in the error rate performances of the models were derived. Expand
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
TLDR
This review, which focuses on the application of CNNs to image classification tasks, covers their development, from their predecessors up to recent state-of-the-art deep learning systems. Expand
Convolutional neural networks with extra-classical receptive fields
TLDR
The proposed model (CNNEx) combines traditional supervised learning via backpropagation with a specialized unsupervised learning rule to learn lateral connections between neurons within a convolutional neural network, which is shown to optimally integrate information from the surround. Expand
Convolutional Neural Networks-An Extensive arena of Deep Learning. A Comprehensive Study
TLDR
A thorough description of CNN implementations in several application areas is offered and a systematic quantitative and performance analysis of the articles selected for this study is performed. Expand
LeanConvNets: Low-Cost Yet Effective Convolutional Neural Networks
TLDR
LeanConvNets that are derived by sparsifying fully-coupled operators in existing CNNs are introduced and it is demonstrated that the resulting LeanConvNet’s accuracy is close to state-of-the-art networks while being computationally less expensive. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 473 REFERENCES
Exploring convolutional neural network structures and optimization techniques for speech recognition
TLDR
This paper investigates several CNN architectures, including full and limited weight sharing, convolution along frequency and time axes, and stacking of several convolution layers, and develops a novel weighted softmax pooling layer so that the size in the pooled layer can be automatically learned. Expand
Very Deep Convolutional Networks for Natural Language Processing
TLDR
This work presents a new architecture for text processing which operates directly on the character level and uses only small convolutions and pooling operations, and is able to show that the performance of this model increases with the depth. Expand
Deep Learning using Linear Support Vector Machines
  • Y. Tang
  • Computer Science, Mathematics
  • 2013
TLDR
The results using L2-SVMs show that by simply replacing softmax with linear SVMs gives significant gains on popular deep learning datasets MNIST, CIFAR-10, and the ICML 2013 Representation Learning Workshop's face expression recognition challenge. Expand
Very deep convolutional neural networks for robust speech recognition
  • Y. Qian, P. Woodland
  • Computer Science
  • 2016 IEEE Spoken Language Technology Workshop (SLT)
  • 2016
TLDR
The extension and optimisation of previous work on very deep convolutional neural networks for effective recognition of noisy speech in the Aurora 4 task are described and it is shown that state-level weighted log likelihood score combination in a joint acoustic model decoding scheme is very effective. Expand
Advances in Very Deep Convolutional Neural Networks for LVCSR
TLDR
This paper proposes a new CNN design without timepadding and without timepooling, which is slightly suboptimal for accuracy, but has two significant advantages: it enables sequence training and deployment by allowing efficient convolutional evaluation of full utterances, and, it allows for batch normalization to be straightforwardly adopted to CNNs on sequence data. Expand
Striving for Simplicity: The All Convolutional Net
TLDR
It is found that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks. Expand
ImageNet classification with deep convolutional neural networks
TLDR
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. Expand
Fast Training of Convolutional Networks through FFTs
TLDR
This work presents a simple algorithm which accelerates training and inference by a significant factor, and can yield improvements of over an order of magnitude compared to existing state-of-the-art implementations. Expand
New types of deep neural network learning for speech recognition and related applications: an overview
TLDR
An overview of the invited and contributed papers presented at the special session at ICASSP-2013, entitled “New Types of Deep Neural Network Learning for Speech Recognition and Related Applications,” as organized by the authors is provided. Expand
Flexible, High Performance Convolutional Neural Networks for Image Classification
We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in aExpand
...
1
2
3
4
5
...