Open AccessPosted Content
Factorized Convolutional Neural Networks
TL;DR: In this paper, the authors propose to factorize the convolutional layers to improve their efficiency, by unravelling them apart, the proposed layer only involves single in-channel convolution and linear channel projection.
read more
Abstract: Deep convolutional neural networks achieve better than human level visual recognition accuracy, at the cost of high computational complexity. We propose to factorize the convolutional layers to improve their efficiency. In traditional convolutional layers, the 3D convolution can be considered as performing in-channel spatial convolution and linear channel projection simultaneously, leading to highly redundant computation. By unravelling them apart, the proposed layer only involves single in-channel convolution and linear channel projection. When stacking such layers together, we achieves similar accuracy with significantly less computation. Additionally, we propose a topological connection framework between the input channels and output channels that further improves the layer's efficiency. Our experiments demonstrate that the proposed method remarkably outperforms the standard convolutional layer with regard to accuracy/complexity ratio. Our model achieves accuracy of GoogLeNet while consuming 3.4 times less computation.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Posted Content
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew Howard,Menglong Zhu,Bo Chen,Dmitry Kalenichenko,Weijun Wang,Tobias Weyand,M. Andreetto,Hartwig Adam +7 more
TL;DR: This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.
18.5K
•Posted Content
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
TL;DR: An extremely computation-efficient CNN architecture named ShuffleNet is introduced, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs), to greatly reduce computation cost while maintaining accuracy.
4.6K
•Posted Content
Xception: Deep Learning with Depthwise Separable Convolutions
TL;DR: Xception as mentioned in this paper proposes a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions, which can be interpreted as an Inception module with a maximally large number of towers.
3.9K
•Posted Content
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
TL;DR: DeepLabv3+ as discussed by the authors extends DeepLab v3+ by adding a simple decoder module to refine the segmentation results especially along object boundaries and further explore the Xception model and apply the depthwise separable convolution to both Atrous spatial pyramid pooling and decoder modules, resulting in a faster and stronger encoder-decoder network.
2.4K
CNN with depthwise separable convolutions and combined kernels for rating prediction
TL;DR: In this paper, a CNN based architecture with depthwise separable convolutions and combined kernels (CNN-DSCK) is proposed for rating prediction exploiting product reviews. But, the proposed method requires two parallel CNNs to extract semantic features from the text reviews of users and items using different kernels in parallel and then select the important information from these features through pooling.
77
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
•Posted Content
Caffe: Convolutional Architecture for Fast Feature Embedding
Yangqing Jia,Evan Shelhamer,Jeff Donahue,Sergey Karayev,Jonathan Long,Ross Girshick,Sergio Guadarrama,Trevor Darrell +7 more
TL;DR: Caffe as discussed by the authors is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.
13.1K
•Proceedings Article
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Christian Szegedy,Sergey Ioffe,Vincent Vanhoucke,Alexander A. Alemi +3 more
- 23 Feb 2016
TL;DR: In this paper, the authors show that training with residual connections accelerates the training of Inception networks significantly, and they also present several new streamlined architectures for both residual and non-residual Inception Networks.