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
Proceedings ArticleDOI
On the Efficacy of Knowledge Distillation
Jang Hyun Cho,Bharath Hariharan +1 more
TL;DR: It is found crucially that larger models do not often make better teachers, and that small students are unable to mimic large teachers.
Posted Content
GraphSAINT: Graph Sampling Based Inductive Learning Method
TL;DR: GraphSAINT is proposed, a graph sampling based inductive learning method that improves training efficiency in a fundamentally different way and can decouple the sampling process from the forward and backward propagation of training, and extend GraphSAINT with other graph samplers and GCN variants.
Posted Content
Born Again Neural Networks
TL;DR: Born-Again Networks (BANs) as mentioned in this paper outperform their teachers significantly, both on computer vision and language modeling tasks, and demonstrate state-of-the-art performance on both predicted and non-predicted classes.
Journal ArticleDOI
REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs
José Ignacio Orlando,Huazhu Fu,João Barbossa Breda,Karel Van Keer,Deepti R. Bathula,Andres Diaz-Pinto,Ruogu Fang,Pheng-Ann Heng,Jeyoung Kim,Joon-Ho Lee,Joonseok Lee,Xiaoxiao Li,Peng Liu,Shuai Lu,Balamurali Murugesan,Valery Naranjo,Sai Samarth R. Phaye,Sharath M Shankaranarayana,Apoorva Sikka,Jaemin Son,Anton van den Hengel,Shujun Wang,Junyan Wu,Zifeng Wu,Guanghui Xu,Yongli Xu,Pengshuai Yin,Fei Li,Xiulan Zhang,Yanwu Xu,Hrvoje Bogunovic +30 more
TL;DR: It is observed that two of the top-ranked teams outperformed two human experts in the glaucoma classification task, and the segmentation results were in general consistent with the ground truth annotations, with complementary outcomes that can be further exploited by ensembling the results.
Journal ArticleDOI
Using deep transfer learning for image-based plant disease identification
TL;DR: This work study transfer learning of the deep convolutional neural networks for the identification of plant leaf diseases and consider using the pre-trained model learned from the typical massive datasets, and then transfer to the specific task trained by the authors' own 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).