MoonJian's Blog
  • Home
  • Archives
  • Categories
  • Tags
  • About
  • 每日一得
  • 阅读
  • 电影
  •   
  •   

(Paper-Reading) A Comprehensive Analysis of Deep Regression

Introduction Regression could also be formulated as classification, why should we dig into this topic? First, there is an inherent trade-off between the complexity of the optimization problem and the

2022-04-04

(Paper Reading) Future Research Directions on Domain Generalization

最近在研究领域泛化,想找个方向做点东西,于是整理了最近看的一篇综述Domain Generalization in Vision: A Survey[1],希望能从中有所收获。 发展方向作者从三个方面进行了总结:模型结构、学习方法和评价基准(Benchmark)。 模型结构动态结构(Dynamic Architectures)在源域训练好后,神经网络的参数通常就固定了下来,充当一个特征提取器,直接

2022-01-05
Tech DL DG
paper

(Paper Reading) Adaptive Methods for Real-World Domain Generalization

Introduction 建立了一个DG大规模数据集Geo-YFCC,考虑到了长尾分布 用了最naive的方法ERM,但却取得了非常好的效果 “In our work, we propose an adaptive classifier that can be adapted to any new domain using very few unlabelled samples without a

2021-12-30
Tech DL DG
paper

(Paper Reading) 近期关于领域泛化文章的归纳整理

Introduction领域泛化(Domain Generalization, DG),不同于领域自适应(Domain Adaptation, DA),在训练过程中无法接触到目标域的数据,因此比DA更加困难,是一个新坑。 Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (T3A)High

2021-12-22
Tech DL DG
paper summary

(Paper Reading) Efficient Deep Learning Survey A Survey on Making Deep Learning Models Smaller, Faster, and Better

Published by Google Research. 1. Main challenges in deep learning areas Sustainable Server-Side Scaling. deploying and letting inference run for over a long period of time could still turn out to be e

2021-12-04
Tech DL Compression
paper google

Github + Hexo 搭建博客踩坑指南

开博语之前是用阿里云的服务器搭建博客,但学生优惠用完了,年费太贵,遂白嫖GitHub重新搭建博客。回顾之前的写作内容,深感个人输出能力极其欠缺,故借再开博客之机,重整旗鼓,用心写作,以练世事之洞察、情理之分析、表达之逻辑! 搭建博客中的坑Github+Hexo的组合网上已有许多资料,我参考的是这份知乎高赞教程[1],但在具体搭建过程中依然踩了不少坑,我将填这些坑的方案整理了一下,你如若也踩到了相似

2021-11-03
Others blog
blog pit github hexo

Search

Hexo Fluid
总访问量 次 总访客数 人
苏ICP备19046742号 苏公网安备19046742号