526互联

GENERALIZATION

SHARPNESS-AWARE MINIMIZATION FOR EFFICIENTLY IMPROVING GENERALIZATION论文阅读笔记

Intro 在训练集上最小化损失很可能导致泛化性低，因为当今模型的过参数化会导致training loss的landscape异常复杂且非凸，包含很多local/global minima，因此优化器的选择至关重要。loss landscape的几何性质（特别是minima的flatness）与泛化 ......
SHARPNESS-AWARE GENERALIZATION MINIMIZATION EFFICIENTLY SHARPNESS

[论文阅读] PCL: Proxy-based Contrastive Learning for Domain Generalization

PCL: Proxy-based Contrastive Learning for Domain Generalization abstract 领域泛化是指从不同源领域的集合中训练模型，该模型可以直接泛化到未见过的目标领域的问题。一种有前途的解决方案是对比学习，它试图通过利用不同领域之间的样本对之 ......
Generalization Contrastive Proxy-based Learning Domain

[论文阅读] Generalizing to Unseen Domains: A Survey on Domain Generalization

Generalizing to Unseen Domains: A Survey on Domain Generalization 代码地址：https://github.com/jindongwang/transferlearning/tree/master/code/DeepDG I. Intr ......
Generalization Generalizing Domains Domain Unseen

[论文阅读] Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization

Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization 论文源码：https://github.com/YBZh/EFDM 1. Introduction 传统的特征分布匹配 ......
Generalization Distribution Arbitrary Matching Transfer

Spectrum Random Masking for Generalization in Image-based Reinforcement Learning

郑重声明：原文参见标题，如有侵权，请联系作者，将会撤销发布！ ......
Generalization Reinforcement Image-based Spectrum Learning

迁移学习（PCL）《PCL: Proxy-based Contrastive Learning for Domain Generalization》

论文信息 论文标题：PCL: Proxy-based Contrastive Learning for Domain Generalization论文作者：论文来源：论文地址：download 论文代码：download引用次数： 1 前言 域泛化是指从一组不同的源域中训练一个模型，可以直接推广到不 ......
Generalization Contrastive Proxy-based PCL Learning

迁移学习（DIFEX）《Domain-invariant Feature Exploration for Domain Generalization》【已复现迁移】

论文信息 论文标题：Domain-invariant Feature Exploration for Domain Generalization论文作者：Wang Lu, Jindong Wang, Haoliang Li, Yiqiang Chen, Xing Xie论文来源：TMLR 2022论 ......
Domain Domain-invariant Generalization Exploration invariant
共7篇  :1/1页 首页上一页1下一页尾页