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
Calibrating Deep Neural Networks using Focal Loss
Jishnu Mukhoti,Viveka Kulharia,Amartya Sanyal,Stuart Golodetz,Philip H. S. Torr,Puneet K. Dokania +5 more
TL;DR: This work provides a thorough analysis of the factors causing miscalibration of Deep Neural Networks, and provides a principled approach to automatically select the hyperparameter involved in the loss function.
Journal ArticleDOI
Concept Whitening for Interpretable Image Recognition.
Zhi Chen,Yijie Bei,Cynthia Rudin +2 more
TL;DR: This work introduces a mechanism, called concept whitening (CW), to alter a given layer of the network to allow us to better understand the computation leading up to that layer and can provide a much clearer understanding for how the network gradually learns concepts over layers.
Proceedings ArticleDOI
SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation
Liang Du,Jingang Tan,Hongye Yang,Jianfeng Feng,Xiangyang Xue,Qibao Zheng,Xiaoqing Ye,Xiaolin Zhang +7 more
TL;DR: A Separated Semantic Feature based domain adaptation network, named SSF-DAN, for semantic segmentation, designed to independently adapt semantic features across the target and source domains and demonstrates robust performance, superior to state-of-the-art methods on benchmark datasets.
Journal ArticleDOI
Blockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging
Rajesh Kumar,Abdullah Aman Khan,Jay Kumar,Zakria,Noorbakhsh Amiri Golilarz,Simin Zhang,Yang Ting,Chengyu Zheng,Wenyong Wang +8 more
TL;DR: A framework that collects a small amount of data from different sources and trains a global deep learning model using blockchain-based federated learning and uses Capsule Network-based segmentation and classification to detect COVID-19 patients and designs a method that can collaboratively train a global model using Blockchain technology with Federated learning while preserving privacy.
Journal ArticleDOI
INet: Convolutional Networks for Biomedical Image Segmentation
Weihao Weng,Xin Zhu +1 more
TL;DR: In this article, the authors propose to enlarge receptive fields by increasing the kernel sizes of convolutional layers in steps (e.g., from $3\times 3$ to $7\times 7$ and then $15\times 15$ ) instead of downsampling.
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).