Densely Connected Convolutional Networks
Gao Huang,Zhuang Liu,Laurens van der Maaten,Kilian Q. Weinberger +3 more
- pp 2261-2269
TLDR
DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.Abstract:
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections—one between each layer and its subsequent layer—our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less memory and computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.read more
Citations
More filters
Journal ArticleDOI
A Particle Swarm Optimization-Based Flexible Convolutional Autoencoder for Image Classification
TL;DR: In this paper, the authors proposed a flexible convolutional autoencoder (FCAE) by eliminating the constraints on the number of convolution layers and pooling layers from the traditional CAE and designed an architecture discovery method by exploiting particle swarm optimization.
Journal ArticleDOI
Open resource of clinical data from patients with pneumonia for the prediction of COVID-19 outcomes via deep learning.
Wanshan Ning,Shijun Lei,Jingjing Yang,Jingjing Yang,Yukun Cao,Peiran Jiang,Qianqian Yang,Jiao Zhang,Xiaobei Wang,Fenghua Chen,Zhi Geng,Liang Xiong,Hongmei Zhou,Yaping Guo,Yulan Zeng,Heshui Shi,Lin Wang,Yu Xue,Zheng Wang +18 more
TL;DR: An open resource containing data from 1,521 patients with pneumonia consisting of chest computed tomography images, 130 clinical features and laboratory-confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) clinical status is described.
Proceedings ArticleDOI
Few Sample Knowledge Distillation for Efficient Network Compression
TL;DR: In this article, a 1x1 convolution layer is added at the end of each layer block of the student-net, and the block-level outputs are fit to the teacher-net by estimating the parameters of the added layers.
Posted Content
Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions.
TL;DR: This work parameterize the Log-Sum-Exp pooling function with a learnable lower-bounded adaptation to build in a sharpness prior and better handle localizing abnormalities of different sizes using only image-level labels to set the state of the art on chest x-rays.
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
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
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.
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.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).