「DL」 卷积网络资源汇总
1 综述
-
Notes on Convolutional Neural Networks
2006-11-22 Paper | 亦轩Dhc
$\bullet \bullet$
主要讲了 CNN 前向和反向传播,包括卷积层和池化的反向传播的推导的讲解; -
A Selective Overview of Deep Learning
2019-04-10 paper -
A review of modularization techniques in artificial neural networks
2019-04-29 paper -
What does it mean to understand a neural network?
2019-07-15 DeepMind, 宾夕法尼亚 paper -
What Do We Understand About Convolutional Networks?
2019-09-09 paper
2 理论
2.1 深与浅
-
The Power of Depth for Feedforward Neural Networks
COLT 2016 2015-12-12 paper
证明了存在 3 层的网络,是无法被 2 层网络逼近的; -
Benefits of depth in neural networks
COLT 2016 2016-02-14 paper
深度网络需要很少的节点就能构造出复杂网络,扁平网络则需要更多节点; -
Learning Functions: When Is Deep Better ThanShallow
2016-03-03 paper -
Deep vs. shallow networks : An approximation theory perspective
2016-08-10 paper -
Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks
ICML 2017 2016-10-31 paper | openreview
对于球状空间,深度可以很好拟合,而扁平网络做不到; -
Learning Functions: When Is Deep Better Than Shallow
2016-03-03 paper -
When and Why Are Deep Networks Better than Shallow Ones
AAAI 2017 2017 paper -
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
2017-03-27 paper | home
3 二维
3.1 经典网络
-
ImageNet classification with deep convolutional neural networks
2012 paper | tensorflow
AlexNet; -
Very deep convolutional networks for large-scale image recognition
ICLR 2015 oral 2014-09-04 paper | tensorflow
VGG: -
Going deeper with convolutions
CVPR 2015 2014-09-17 paper
GoogLeNet; -
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
2015-02-11 paper | blog-Michael | blog-极市
提出了批量归一化,被大量使用;
InceptionV2 -
Deep residual learning for image recognition
CVPR 2016 2015-12-10 paper
ResNet; -
Densely Connected Convolutional Networks
CVPR 2017 2016-08-25 paper
DenseNet -
Deep Pyramidal Residual Networks
CVPR 2017 2016-10-10 paper
解决残差设计中遇到通道升维时效果不好的问题;
PyramidNet -
Dual Path Networks
2017-07-06 paper | mxnet-official
DualPathNet -
Squeeze-and-Excitation Networks
2017-09-05 Paper
SENet
3.2 轻量级网络
-
Aggregated Residual Transformations for Deep Neural Networks
CVPR 2017 2016-11-16 paper
ResNeXt; -
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
ICLR 2017 2016-02-24 伯克利&斯坦福 paper
SqueezeNet -
Xception: Deep Learning with Depthwise Separable Convolutions
2016-10-07 Google paper
Xception -
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
CVPR 2017 2017-04-17 paper | ncnn-Blog | caffe
MobileNet -
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
CVPR 2017 2017-07-04 Face++ paper
ShuffleNet -
Interleaved Group Convolutions for Deep Neural Networks
ICCV 2017 2017-07-10 微软 paper | mxnet
IGCV -
CondenseNet: An Efficient DenseNet using Learned Group Convolutions
2017-11-25 paper | pytorch
CondenseNet -
MobileNetV2: Inverted Residuals and Linear Bottlenecks
2018-01-13 paper | mxnet | caffe
MobileNetV2 -
IGCV2: Interleaved Structured Sparse Convolutional Neural Networks
2018-04-17 微软 paper
IGCV2 -
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
BMVC 2018 2018-06-01 微软 paper | mxnet | pytorch
IGCV3 -
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
2018-07-30 paper
ShuffleNetV2 -
Searching for MobileNetV3
2019-05-06 google paper | pytorch | pytorch | 我爱计算机视觉
MobileNetV3: -
MoGA: Searching Beyond MobileNetV3
2019-08-04 paper | pytorch-official
3.3 提升泛化能力
-
Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks
2019-06-30 paper
设计了新的 loss 来指导网络学习更多的相关特征,以应对未见过的数据; -
Sparsifying and Down-scaling Networks to Increase Robustness to Distortions
2020-06-08 paper
抗噪声,提出了 STNet,用于修改网络的 block 提升噪声鲁棒;
3.4 注意力
- ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
2019-10-08 paper | pytorch-official
反思注意力带来的计算冗余问题;
3.5 其他
- Multi-column Deep Neural Networks for Image Classification
CVPR 2012 2012-02-13 paper | blog | bagging | blog | blog
数据集:MNIST,NIST SD 19,CASIA(中国字),GTSRB(路标),CIFAR 10(natural color images),NORB(stereo images of 3D models)
IJCNN 2012 第一名,准确率 99.46% 优于人类识别率;多个 DNNs 结合到一个MCDNN(MLP+DNN);初评时,作者使用了一组 trained on provided features的多层感知器(MLP)和一个 DNN trained on raw pixel intensities;本篇论文描述的是现场总决赛阶段使用的方法,MCDNN;
1.Invertible Residual Networks
ICML 2019 2018-11-02 paper
4 三维
-
3D Dense Separated Convolution Module for Volumetric Image Analysis
2019-05-14 paper -
A review on deep learning techniques for 3D sensed data classification
2019-07-09 paper
5 四元组
-
Quaternion Recurrent Neural Networks
2018-06-12 paper -
Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition
2018-06-20 paper -
Quaternion Convolutional Neural Networks
ECCV 2018 2018-08 paper | paper-eccv | 机构 | blog
$\bullet \bullet$ QCNN
针对 CNN 中通道处理太简单(相加)而存在的多个弊端,本文借鉴机器人学中的四元数来表示彩色图像,并给除了前向和反向传播推导;与 CNN 做了对比实验,在彩色图像去噪和分类任务上表现都更好; -
A survey of quaternion neural networks
2019-08-06
$\bullet \bullet$
Comments