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
CMOS-integrated memristive non-volatile computing-in-memory for AI edge processors
Wei-Hao Chen,Chunmeng Dou,K. C. Li,Wei-Yu Lin,Pin-Yi Li,Jian-Hao Huang,Jing-Hong Wang,Wei-Chen Wei,Cheng-Xin Xue,Yen-Cheng Chiu,Ya-Chin King,Chorng-Jung Lin,Ren-Shuo Liu,Chih-Cheng Hsieh,Kea-Tiong Tang,Jianhua Yang,Mon-Shu Ho,Meng-Fan Chang +17 more
TL;DR: A fully integrated memristive nvCIM structure that integrates a resistive memory array with control and readout circuits using an established 65 nm foundry CMOS process, can offer high energy efficiency and low latency for Boolean logic and multiply-and-accumulation operations.
Book ChapterDOI
Deforming autoencoders: Unsupervised disentangling of shape and appearance
Zhixin Shu,Mihir Sahasrabudhe,Riza Alp Guler,Dimitris Samaras,Nikos Paragios,Iasonas Kokkinos +5 more
TL;DR: Deforming autoencoders as mentioned in this paper disentangle shape from appearance in an unsupervised manner by representing shape as a deformation between a canonical coordinate system and an observed image, while appearance is modeled in deformation-invariant, template coordinates.
Journal ArticleDOI
Adversarial Examples: Opportunities and Challenges
Jiliang Zhang,Chen Li +1 more
TL;DR: The concept, cause, characteristics, and evaluation metrics of AEs are introduced, then a survey on the state-of-the-art AE generation methods with the discussion of advantages and disadvantages are given.
Proceedings ArticleDOI
Dual Super-Resolution Learning for Semantic Segmentation
TL;DR: A simple and flexible two-stream framework named Dual Super-Resolution Learning (DSRL) to effectively improve the segmentation accuracy without introducing extra computation costs and can be easily generalized to other tasks, e.g., human pose estimation.
Book ChapterDOI
Quantized Densely Connected U-Nets for Efficient Landmark Localization
TL;DR: This paper proposes quantized densely connected U-Nets for efficient visual landmark localization with order-K dense connectivity to trim off long-distance shortcuts and uses a memory-efficient implementation to significantly boost the training efficiency and investigates an iterative refinement that may slice the model size in half.
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).