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
DENSE-INception U-net for medical image segmentation.
TL;DR: The experiments highlighted that combining the inception module with dense connections in the U-Net architecture is a promising approach for semantic medical image segmentation.
Posted ContentDOI
CORnet: Modeling the Neural Mechanisms of Core Object Recognition
Jonas Kubilius,Jonas Kubilius,Martin Schrimpf,Aran Nayebi,Daniel M. Bear,Yamins Dlk,James J. DiCarlo,James J. DiCarlo +7 more
TL;DR: The current best ANN model derived from this approach (CORnet-S) is among the top models on Brain-Score, a composite benchmark for comparing models to the brain, but is simpler than other deep ANNs in terms of the number of convolutions performed along the longest path of information processing in the model.
Posted Content
ACFNet: Attentional Class Feature Network for Semantic Segmentation
TL;DR: This paper presents the concept of class center which extracts the global context from a categorical perspective, and proposes a novel module, named Attentional Class Feature (ACF) module, to calculate and adaptively combine different class centers according to each pixel.
Posted Content
MixConv: Mixed Depthwise Convolutional Kernels
Mingxing Tan,Quoc V. Le +1 more
TL;DR: MixConv as discussed by the authors proposes a new mixed depthwise convolution, which naturally mixes up multiple kernel sizes in a single convolution and improves the accuracy and efficiency for existing MobileNets on both ImageNet classification and object detection.
Posted Content
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Alvin Wan,Xiaoliang Dai,Peizhao Zhang,Zijian He,Yuandong Tian,Saining Xie,Bichen Wu,Matthew Yu,Tao Xu,Kan Chen,Peter Vajda,Joseph E. Gonzalez +11 more
TL;DR: This work proposes a memory and computationally efficient DNAS variant, DMaskingNAS, that expands the search space by up to 10^14x over conventional DNAS, supporting searches over spatial and channel dimensions that are otherwise prohibitively expensive: input resolution and number of filters.
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).