文件名称：卷积网络模型.zip
文件大小：11.7MB
文件格式：ZIP
更新时间：2020-03-14 13:30:15
深度学习
再思考计算机视觉的Inception结构 Rethinking the inception architecture for computer vision (2016) 作者C. Szegedy et al. 摘要：对于多种任务来说，卷及网络处于最先进的计算机视觉解决方案的核心。自2014年以来，超深度卷积网络开始成为主流，在各种benchmark中产生了巨大的收获。虽然对大多数任务来说，增加的模型大小和计算成本往往转化为直接增益（只要提供足够的标记数据用于训练），计算效率和低参数计数仍然是各种用例的有利因素，例如移动视觉和大数据场景。在这里，我们将探讨通过适当的因式分解卷积和积极正则化的方式，尽可能有效地利用增加的算力来扩大网络规模。我们在ILSVRC 2012分类挑战验证集上的benchmark了我们的方法，展示了相对于现有技术的实质性增益：每次推理使用50亿multiply-adds的计算成本及使用少于2500万个参数，每单帧错位率为21.2％top-1和5.6％top-5。综合使用4种模型和multi-crop 评估的综合，我们在验证集上报告3.5％的top-5错误和17.3％的top-1错误，以及正式测试集上3.6％的top-5 错误。 Inception-v4, inception-resnet以及残差连接对学习的影响 Inception-v4, inception-resnet and the impact of residual connections on learning (2016) 作者C. Szegedy et al. 在深度残差网络中识别映射 Identity Mappings in Deep Residual Networks (2016) 作者K. He et al. 图像识别中的深度残差学习 Deep residual learning for image recognition (2016) 作者K. He et al. 深入卷积网络 Going deeper with convolutions (2015) 作者C. Szegedy et al. 大规模图像识别的超深度卷积网络 Very deep convolutional networks for large-scale image recognition (2014) 作者K. Simonyan and A. Zisserman 用于视觉识别的深度卷积网络的空间金字塔池化 Spatial pyramid pooling in deep convolutional networks for visual recognition (2014) 作者K. He et al. 细节魔鬼的回归：深挖卷积网络 Return of the devil in the details: delving deep into convolutional nets (2014) 作者K. Chatfield et al. OverFeat：使用卷积网络融合识别、本地化和检测 OverFeat: Integrated recognition, localization and detection using convolutional networks (2013) 作者P. Sermanet et al. Maxout网络 Maxout networks (2013) 作者I. Goodfellow et al. 深度网络架构 Network in network (2013) 作者M. Lin et al. 使用深度卷积神经网络进行ImageNet 分类 ImageNet classification with deep convolutional neural networks (2012) 作者A. Krizhevsky et al.
【文件预览】：
卷积网络模型
----Maxout networks (2013), I. Goodfellow et al..pdf(1.16MB)
----.DS_Store(14KB)
----._Maxout networks (2013), I. Goodfellow et al..pdf(4KB)
----._Very deep convolutional networks for large-scale image recognition (2014), K. Simonyan and A. Zisserman.pdf(4KB)
----._Deep residual learning for image recognition (2016), K. He et al..pdf(4KB)
----Very deep convolutional networks for large-scale image recognition (2014), K. Simonyan and A. Zisserman.pdf(195KB)
----Return of the devil in the details- delving deep into convolutional nets (2014), K. Chatfield et al..pdf(441KB)
----OverFeat- Integrated recognition, localization and detection using convolutional networks (2013), P. Sermanet et al. .pdf(916KB)
----._Identity Mappings in Deep Residual Networks (2016), K. He et al. .pdf(4KB)
----Rethinking the inception architecture for computer vision (2016), C. Szegedy et al..pdf(519KB)
----._Rethinking the inception architecture for computer vision (2016), C. Szegedy et al..pdf(4KB)
----._.DS_Store(4KB)
----ImageNet classification with deep convolutional neural networks (2012), A. Krizhevsky et al. .pdf(1.35MB)
----Deep residual learning for image recognition (2016), K. He et al..pdf(800KB)
----Spatial pyramid pooling in deep convolutional networks for visual recognition (2014), K. He et al..pdf(3.97MB)
----._Spatial pyramid pooling in deep convolutional networks for visual recognition (2014), K. He et al..pdf(4KB)
----._Szegedy_Going_Deeper_With_2015_CVPR_paper.pdf(4KB)
----._Inception-v4, inception-resnet and the impact of residual connections on learning (2016), C. Szegedy et al..pdf(4KB)
----Inception-v4, inception-resnet and the impact of residual connections on learning (2016), C. Szegedy et al..pdf(935KB)
----Szegedy_Going_Deeper_With_2015_CVPR_paper.pdf(1.24MB)
----._Return of the devil in the details- delving deep into convolutional nets (2014), K. Chatfield et al..pdf(4KB)
----._ImageNet classification with deep convolutional neural networks (2012), A. Krizhevsky et al. .pdf(4KB)
----._OverFeat- Integrated recognition, localization and detection using convolutional networks (2013), P. Sermanet et al. .pdf(4KB)
----Identity Mappings in Deep Residual Networks (2016), K. He et al. .pdf(1.1MB)
----Network in network (2013), M. Lin et al..pdf(581KB)
----._Network in network (2013), M. Lin et al..pdf(4KB)