automl -综述

参考文献

综述

多papers—自动机器学习: 最新进展综述与开放挑战 | AutoML

(1)2018综述文章:Taking Human out of Learning Applications: A Survey on Automated Machine Learning
原文:yhttps://arxiv.org/abs/1810.13306v1
解读1:http://www.aibbt.com/a/48548.html
解读2:https://www.jianshu.com/p/7df532c436f5

(2)2019综述文章:AutoML: A Survey of the State-of-the-Art
原文:https://arxiv.org/pdf/1908.00709.pdf
解读0(简明,有引用文献):AutoML: A Survey of the state-of-the-art
解读1(详细):AutoML:最新技术概览
解读2(简洁有条理):AutoML自动机器学习:最新进展综述
(2.1)2019综述:Neural Architecture Search: A Survey
解读:Neural Architecture Search: A Survey (神经网络结构搜索survey)
(2.2)2019综述:A Survey on Neural Architecture Search (Wistuba et al. 2019)

神经网络架构搜索(Neural Architecture Search)杂谈

(4)【小结】除了网络搜索(NAS),AutoML对深度学习模型优化还有哪些贡献?

automl应用

除了网络搜索(NAS),AutoML对深度学习模型优化还有哪些贡献?
AutoML - 数据增广
论文 | 用于移动端模型自动压缩与加速的AutoML

  • automl与目标检测
  1. Auto-FPN: Automatic Network Architecture Adaptation for Object
    Detection (ICCV2019)

  2. DetNAS: Backbone Search for Object Detection (NIPS19)
    github地址:https://github.com/megvii-model/DetNAS

  3. Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection (Arxiv)

  4. EfficientDet: Scalable and Efficient Object Detection (Arxiv)

  5. MnasFPN : Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices (Arxiv)

  6. NAS-FCOS: Fast Neural Architecture Search for Object Detection (Arxiv)
    github:https://github.com/Lausannen/NAS-FCOS

  7. NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection (CVPR2019)

  8. SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection (AAAI2020)

  • 语义分割
  1. Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
  • 行人重识别
  1. Auto-ReID: Searching for a Part-Aware ConvNet for Person Re-Identification
  • 识别与定位
  1. SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization (Arxiv)
  2. 比手工模型快10~100倍,谷歌揭秘视频NAS三大法宝

资源

自动化机器学习(AutoML)文献/工具/项目资源大列表分享
非常全面的AutoML资源,看这个就够了!

AutoML研究分析—auto-keras怎么用的

github论文荟萃:
https://github.com/hibayesian/awesome-automl-papers
https://github.com/windmaple/awesome-AutoML
https://github.com/guan-yuan/awesome-AutoML-and-Lightweight-Models

新研究与新papers

谷歌开源 MobileNetV3:新思路 AutoML 改进计算机视觉模型移动端
你想要的神经网络自动设计,谷歌大脑帮你实现了:用参数共享高效地搜索神经网络架构(ENAS)

发布了180 篇原创文章 · 获赞 309 · 访问量 27万+

猜你喜欢

转载自blog.csdn.net/xys430381_1/article/details/103544069