READING NOTE: Aggregated Residual Transformations for Deep Neural Networks
来源:互联网 发布:施耐德plc仿真软件 编辑:程序博客网 时间:2024/05/16 14:40
TITLE: Aggregated Residual Transformations for Deep Neural Networks
AUTHOR: Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, Kaiming He
ASSOCIATION: UC San Diego, Facebook AI Research
FROM: arXiv:1611.05431
CONTRIBUTIONS
A simple, highly modularized network (ResNeXt) architecture for image classification is proposed. The network is constructed by repeating a building block that aggregates a set of transformations with the same topology.
METHOD
The network is designed with two simple rules inspired by VGG/ResNets:
- if producing spatial maps of the same size, the blocks share the same hyper-parameters (width and filter sizes).
- each time when the spatial map is downsampled by a factor of 2, the width of the blocks is multiplied by a factor of 2. The second rule ensures that the computational complexity, in terms of FLOPs is roughly the same for all blocks.
The building block of ResNeXt is shown in the following figure:
Such design will make the network having more channels (sets of transformations) without increasing much FLOPs, which is claimed as the increasing of ardinality.
SOME IDEAS
The explanation of why such designation can lead to better performance seems to be less pursative.
- READING NOTE: Aggregated Residual Transformations for Deep Neural Networks
- [Paper note] Aggregated Residual Transformations for Deep Neural Networks
- 批量残差网络-Aggregated Residual Transformations for Deep Neural Networks
- READING NOTE: PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
- READING NOTE: Factorized Convolutional Neural Networks
- Reading Note: Interpretable Convolutional Neural Networks
- 《Neural Networks and Deep Learning》codes' note
- READING NOTE: Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Trackin
- Reading Note: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- READING NOTE: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
- Reading Note: ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
- [Paper note] PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection
- deep-residual-networks
- READING NOTE: Chained Predictions Using Convolutional Neural Networks
- READING NOTE: Do semantic parts emerge in Convolutional Neural Networks?
- Deep Neural Networks for YouTube Recommendations
- Deep Residual Networks for Image Classification with Python + NumPy
- Enhanced Deep Residual Networks for Single Image Super-Resolution
- Jquery easyui tree的使用
- python基础知识之整除、取余、幂运算
- class 与 struct的区别
- 对CNN中pooling的理解
- 嵌入式系统
- READING NOTE: Aggregated Residual Transformations for Deep Neural Networks
- (a,b)=1 ax+by x>0 y>0的最大不能表示数
- 总结(一)
- tr命令
- SpannableString与SpannableStringBuilder使用
- Android app fundamentals
- 【转】Oracle表与索引的分析及索引重建
- 总结
- 利用Docker创建hadoop集群