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
Task2Vec: Task Embedding for Meta-Learning
Alessandro Achille,Michael Lam,Rahul Tewari,Avinash Ravichandran,Subhransu Maji,Charless C. Fowlkes,Stefano Soatto,Pietro Perona +7 more
TL;DR: In this article, the authors propose a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations, and demonstrate that this method is capable of predicting task similarities that match our intuition about semantic and taxonomic relations between different visual tasks.
Journal ArticleDOI
Early recognition of tomato gray leaf spot disease based on MobileNetv2-YOLOv3 model
Jun Liu,Xuewei Wang +1 more
TL;DR: This study proposes an early recognition method of tomato leaf spot based on MobileNetv2-YOLOv3 model that improves the accuracy of the regression box of tomato gray leaf spot recognition by introducing the GIoU bounding box regression loss function.
Journal ArticleDOI
Review on Convolutional Neural Network (CNN) Applied to Plant Leaf Disease Classification
TL;DR: This work reviewed the latest CNN networks pertinent to plant leaf disease classification and summarized DL principles involved in plant disease classification, and summarized the main problems and corresponding solutions of CNN used for plant disease classified.
Posted Content
Timeception for Complex Action Recognition
TL;DR: Timeception as discussed by the authors uses multi-scale temporal convolutions and reduces the complexity of 3D convolutions, which achieves impressive accuracy in recognizing the human activities of Charades, Breakfast Actions, and MultiTHUMOS.
Journal ArticleDOI
NFN+: A novel network followed network for retinal vessel segmentation.
TL;DR: The proposed NFN+ model, to the best knowledge, achieved the state-of-the-art retinal vessel segmentation accuracy on color fundus images (AUC: 98.30%, 98.75% and 98.94%, respectively).
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).