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
Posted Content
Efficient Architecture Search by Network Transformation
TL;DR: In this paper, a meta-controller is employed to grow the network depth or layer width with function-preserving transformations, thus saving a large amount of computational cost, which can be reused for further exploration.
Journal ArticleDOI
Evolving Deep Convolutional Neural Networks for Image Classification
TL;DR: In this paper, an efficient variable-length gene encoding strategy is designed to represent the different building blocks and the potentially optimal depth in convolutional neural networks, which is expected to avoid networks getting stuck into local minimum that is typically a major issue in backward gradient-based optimization.
Journal ArticleDOI
A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis.
Shuo Wang,Yunfei Zha,Weimin Li,Qingxia Wu,Xiaohu Li,Meng Niu,Meiyun Wang,Xiaoming Qiu,Hongjun Li,He Yu,Wei Gong,Yan Bai,Li Li,Yongbei Zhu,Liusu Wang,Jie Tian +15 more
TL;DR: A fully automatic deep learning system is proposed for COVID-19 diagnostic and prognostic analysis by routinely used computed tomography that automatically focused on abnormal areas that showed consistent characteristics with reported radiological findings.
Journal ArticleDOI
COVID-19 Detection through Transfer Learning Using Multimodal Imaging Data
Michael J. Horry,Subrata Chakraborty,Manoranjan Paul,Anwaar Ulhaq,Biswajeet Pradhan,Manas Saha,Nagesh Shukla +6 more
TL;DR: This study demonstrates how transfer learning from deep learning models can be used to perform COVID-19 detection using images from three most commonly used medical imaging modes X-Ray, Ultrasound, and CT scan to provide over-stressed medical professionals a second pair of eyes through intelligent deep learning image classification models.
Proceedings ArticleDOI
Exploit the Unknown Gradually: One-Shot Video-Based Person Re-identification by Stepwise Learning
TL;DR: This paper proposes an approach to exploiting unlabeled tracklets by gradually but steadily improving the discriminative capability of the Convolutional Neural Network feature representation via stepwise learning.
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).