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
Lightweight network with one-shot aggregation for image super-resolution
TL;DR: One-shot aggregation network (OAN) as discussed by the authors adopts a one-shot aggregator to combine the intermediate features with multiple receptive fields only once in the last feature map to overcome the inefficiency of dense aggregation.
Proceedings ArticleDOI
An empirical study on global bone age assessment
Felipe Torres,Cristina González,María Escobar,Laura Alexandra Daza,Gustavo Triana,Pablo Arbeláez +5 more
TL;DR: This paper presents GPNet a convolutional neural network capable of performing BAA precisely and effectively by analyzing the whole hand in a single forward pass and develops a method that reduces the number of trainable parameters in comparison to the state-of-the-art, while improving the performance.
Journal ArticleDOI
Finite strain FE2 analysis with data-driven homogenization using deep neural networks
TL;DR: In this article , a data-driven deep neural network (DNN) based approach is presented to accelerate finite element analysis (FE2) by using a probabilistic approach for surrogates' development.
Journal ArticleDOI
Deep learning–based velocity antialiasing of 4D‐flow MRI
Haben Berhane,Michael Scott,Alex J. Barker,Patrick L. McCarthy,Ryan Avery,Bradley D. Allen,S. Chris Malaisrie,Joshua D. Robinson,Cynthia K. Rigsby,Michael Markl +9 more
TL;DR: A convolutional neural network is developed for the robust and fast correction of velocity aliasing in 4D-flow MRI and shows excellent performance for the simulated data compared with the conventional algorithm.
Journal ArticleDOI
Lightweight residual densely connected convolutional neural network
Fahimeh Fooladgar,Shohreh Kasaei +1 more
TL;DR: In this article, the lightweight residual densely connected blocks are proposed to guaranty the deep supervision, efficient gradient flow, and feature reuse abilities of convolutional neural network, which decreases the cost of training and inference processes without using any special hardware-software equipment by just reducing the number of parameters and computational operations.
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).