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
WeatherBench: A Benchmark Data Set for Data-Driven Weather Forecasting
TL;DR: A benchmark data set for data‐driven medium‐range weather forecasting (specifically 3–5 days), a topic of high scientific interest for atmospheric and computer scientists alike, is presented and a simple and clear evaluation metrics are proposed which will enable a direct comparison between different methods.
Proceedings ArticleDOI
MaxViT: Multi-Axis Vision Transformer
TL;DR: This paper introduces an efficient and scalable attention model, which consists of two aspects: blocked local and dilated global attention, and expresses strong generative modeling capability on ImageNet, demonstrating the superior potential of MaxViT blocks as a universal vision module.
Proceedings ArticleDOI
Fast Sparse ConvNets
TL;DR: This work introduces a family of efficient sparse kernels for several hardware platforms, and shows that sparse versions of MobileNet v1 and Mobile net v2 architectures substantially outperform strong dense baselines on the efficiency-accuracy curve.
Posted Content
Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions
TL;DR: This paper proposes an extension of U-Net, Bi-directional ConvLSTM U- net with Densely connected convolutions (BCDU-Net), for medical image segmentation, in which the full advantages of U -Net, bi- directional Conv lSTM (BConvL STM) and the mechanism of dense convolutions are taken.
Journal ArticleDOI
Scoring of tumor-infiltrating lymphocytes: From visual estimation to machine learning
Frederick Klauschen,Klaus-Robert Müller,Alexander Binder,Michael Bockmayr,Miriam Hägele,Philipp Seegerer,Stephan Wienert,Giancarlo Pruneri,S. de Maria,Sunil S. Badve,Stefan Michiels,Torsten O. Nielsen,Sylvia Adams,Peter Savas,Fraser Symmans,Scooter Willis,Tina Gruosso,Morag Park,Benjamin Haibe-Kains,Brandon D. Gallas,Alastair M. Thompson,Ian A. Cree,Christos Sotiriou,Cinzia Solinas,Matthias Preusser,Stephen M. Hewitt,David L. Rimm,Giuseppe Viale,Sherene Loi,Sibylle Loibl,Roberto Salgado,Carsten Denkert +31 more
TL;DR: Different automated TIL scoring approaches are discussed ranging from classical image segmentation, where cell boundaries are identified and the resulting objects classified according to shape properties, to machine learning-based approaches that directly classify cells without segmentation but rely on large amounts of training data.
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).