DL之DenseNet:DenseNet算法的简介(论文介绍)、架构详解、案例应用等配图集合之详细攻略
DL之DenseNet:DenseNet算法的简介(论文介绍)、架构详解、案例应用等配图集合之详细攻略
相关文章
DL之DenseNet:DenseNet算法的简介(论文介绍)、架构详解、案例应用等配图集合之详细攻略
DL之DenseNet:DenseNet算法的架构详解
DenseNet算法的简介(论文介绍)
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 computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.
摘要
最近的研究表明,如果卷积网络在靠近输入和接近输出的层之间包含较短的连接,那么卷积网络可以更深入、更准确和有效地训练。在本文中,我们采用这种观测方法,并引入了紧密卷积网络(densenet),它以一种前馈的方式将每一层连接到另一层。传统的具有L层的卷积网络在每一层和其后续层之间都有L连接,而我们的网络有L(L+1)2个直接连接。对于每个图层,前面所有图层的 feature-maps都用作输入,其自身的 feature-maps也用作后面所有图层的输入。 DenseNets有几个引人注目的优点:它们可以缓解消失梯度问题,加强特征传播,鼓励特征重用,并大幅减少参数数量。我们在四个高度竞争的对象识别基准任务 (CIFAR-10, CIFAR-100, SVHN, and ImageNet)上评估我们提出的体系结构。DenseNets 在大多数方面都比最先进的技术有了显著的改进,同时需要较少的计算来实现高性能。可在https://github.com/liuzhuang13/DenseNet上获取代码和预训练模型。
Conclusion
We proposed a new convolutional network architecture, which we refer to as Dense Convolutional Network (DenseNet). It introduces direct connections between any two layers with the same feature-map size. We showed that DenseNets scale naturally to hundreds of layers, while exhibiting no optimization difficulties. In our experiments,DenseNets tend to yield consistent improvement in accuracy with growing number of parameters, without any signs of performance degradation or overfitting. Under multiple settings, it achieved state-of-the-art results across several highly competitive datasets. Moreover, DenseNets require substantially fewer parameters and less computation to achieve state-of-the-art performances. Because we adopted hyperparameter settings optimized for residual networks in our study, we believe that further gains in accuracy of DenseNets may be obtained by more detailed tuning of hyperparameters and learning rate schedules.
Whilst following a simple connectivity rule, DenseNets naturally integrate the properties of identity mappings, deep supervision, and diversified depth. They allow feature reuse throughout the networks and can consequently learn more compact and, according to our experiments, more accurate models. Because of their compact internal representations and reduced feature redundancy, DenseNets may be good feature extractors for various computer vision tasks that build on convolutional features, e.g., [4, 5]. We plan to study such feature transfer with DenseNets in future work.
结论
我们提出了一种新的卷积网络结构,我们称之为密集卷积网络(DenseNet)。它引入了任何两层之间具有相同feature-map大小的直接连接。我们发现 DenseNets可以自然地扩展到数百层,但不存在优化困难。在我们的实验中,随着参数数量的增加, DenseNets的精确度会持续提高,而不会出现性能下降或过度拟合的迹象。在多个设置下,它在多个高度竞争的数据集中实现了最先进的结果。此外, DenseNets需要更少的参数和更少的计算来实现最先进的性能。因为我们在研究中采用了针对剩余网络进行优化的超参数设置,我们相信通过更详细地调整超参数和学习速率时间表,可以进一步提高 DenseNets的精度。
在遵循简单连接规则的同时, DenseNets自然地整合了身份映射、深度监督和多样化深度的属性。它们允许在整个网络中重复使用功能,因此可以学习更紧凑的,根据我们的实验,更精确的模型。由于其紧凑的内部表示和减少的特征冗余,DenseNets可能是各种计算机视觉任务的很好的特征提取器,这些任务基于卷积特征,例如[4,5]。我们计划在未来的工作中与DenseNets一起研究这种特征转移。
论文
Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Weinberger.
Densely connected convolutional networks. CVPR. 2017 (CVPR Best Paper Award)
https://arxiv.org/pdf/1608.06993.pdf
GitHub
https://github.com/liuzhuang13/DenseNet
DenseNet is a network architecture where each layer is directly connected to every other layer in a feed-forward fashion (within each dense block). For each layer, the feature maps of all preceding layers are treated as separate inputs whereas its own feature maps are passed on as inputs to all subsequent layers. This connectivity pattern yields state-of-the-art accuracies on CIFAR10/100 (with or without data augmentation) and SVHN. On the large scale ILSVRC 2012 (ImageNet) dataset, DenseNet achieves a similar accuracy as ResNet, but using less than half the amount of parameters and roughly half the number of FLOPs.
Densenet是一种网络架构,其中每一层以前馈方式(在每个密集块内)直接连接到其他每一层。对于每个图层,前面所有图层的要素图都被视为单独的输入,而它自己的要素图则作为输入传递给后面所有图层。这种连接模式在CIFAR10/100(有或无数据扩充)和SVHN上产生最先进的精度。在大规模的ILSVRC 2012(ImageNet)数据集上,DenseNet 实现了与ResNet相似的精度,但使用的参数数量不到一半,而使用的触发器数量大约为一半。
DenseNet算法的架构详解
3、DenseNet architectures for ImageNet
The growth rate for all the networks is ????=32. Note that each “conv” layer shown in the table corresponds the sequence BN-ReLU-Conv. 所有网络的增长率为32。请注意,表中所示的每个“conv”层对应于序列BN-ReLU-Conv。
4、实验结果
1、CIFAR-10上的结果
2、ImageNet上的结果
The top-1 and top-5 error rates on the ImageNet validation set, with single-crop / 10-crop testing
ImageNet上的结果:基于DenseNet的分类器只需要ResNet一半的参数量,就可在ImageNet上达到相同分类精度
DenseNet算法的案例应用
后期更新……