Domain Adaptation 2019 Conference Papers

2024-06-05 11:38

本文主要是介绍Domain Adaptation 2019 Conference Papers,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!

本文为转载文章,转自链接: https://blog.csdn.net/weixin_40400177/article/details/103538656
AbbreviationPaper TitleSource LinkCodeTags
DTADrop to Adapt: Learning Discriminative Features for Unsupervised Domain AdaptationICCV2019PyTorch(Official)DTA Adversarial Dropout
BSPTransferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain AdaptationICML2019Pytorch(Official)LDA-SVD->BSP Between-class Within-class
DEVTowards Accurate Model Selection in Deep Unsupervised Domain AdaptationICML2019sklearn(Official)Density-Ratio-Estimation Variance-Reduction
Zhao’sOn Learning Invariant Representation for Domain AdaptationICML2019Code(empty)Theory Conditional-Shfit Information-Theoretic-Lower-Bound
Wu’sDomain Adaptation with Asymmetrically-Relaxed Distribution AlignmentICML2019Theory Label-Shift Asymmetrically-Relaxed-Distances
MDDBridging Theory and Algorithm for Domain AdaptationICML2019Pytorch(Official)Theory Margin-Disparity-Discrepancy Rademacher-Complexity
CADAAttending to Discriminative Certainty for Domain AdaptationCVPR2019 arXivCode(Empty)Region-Adaptation Bayesian-Framework Attention
d-SNEd-SNE: Domain Adaptation Using Stochastic Neighborhood EmbeddingCVPR2019 Oral arXivMXNet-Gluon(Official)Hausdorff-Distance Domain-Generalization
GCANGCAN: Graph Convolutional Adversarial Network for Unsupervised Domain AdaptationCVPR2019Structureaware-Alignment Domain-Alignment Class-Centroid-Alignment
GIO-AdaLearning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation ApproachCVPR2019Geometric-Information Adversarial-Training Depth-and-Semantic-Prediction
DISEAll about Structure: Adapting Structural Information across Domains for Boosting Semantic SegmentationCVPR2019Pytorch(Official)Domain-Invariant-Structure Domain-Specific-Representations
DSBNDomain-Specific Batch Normalization for Unsupervised Domain AdaptationCVPR2019Batch-Normalization Pseudo-Labels
DWTUnsupervised Domain Adaptation using Feature-Whitening and Consensus LossCVPR2019Min-Entropy Consensus loss Domain-Alignment-Layer
BDLBidirectional Learning for Domain Adaptation of Semantic SegmentationCVPR2019Pytorch(Official)Image-Translation Alternative Learning Perceptual-Loss
CANContrastive Adaptation Network for Unsupervised Domain AdaptationCVPR2019Intra-Class-Discrepancy Inter-Class-Discrepancy CDD-Metric
GPDAUnsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process ApproachCVPR2019 OralMCD->GP Classifier’s-Posterior-Distribution
Tran’sJoint Pixel and Feature-level Domain Adaptation in the WildCVPR2019Combining-Many-Method
UANUniversal Domain AdaptationCVPR2019Sample-Level Partial and Open Set
ADVENTADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic SegmentationCVPR2019 OralCode(Empty)Meta-Sub-Target
AMEANBlending-Target Domain Adaptation by Adversarial Meta-Adaptation NetworksCVPR2019 OralPytorch(Official)Multiple Sub-targets Category-Misalignment
TPNTransferrable Prototypical Networks for Unsupervised Domain AdaptationCVPR2019 OralNon-linear-Mapping Pseudo-Label Score-Distribution
PFANProgressive Feature Alignment for Unsupervised Domain AdaptationCVPR2019Intra-Class-Variation Adaptive-Prototype-Alignment Non-Saturated-Classifier
SymNetsDomain-Symmetric Networks for Adversarial Domain AdaptationCVPR2019Pytorch(Official)Symmetric-Classifiers Domain-Confusion Category-Level
CLANTaking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain AdaptationCVPR2019 OralPytorch(Official)Category-Level Co-training
SWDSliced Wasserstein Discrepancy for Unsupervised Domain AdaptationCVPR2019Wasserstein-Discrepancy

这篇关于Domain Adaptation 2019 Conference Papers的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!



http://www.chinasem.cn/article/1032951

相关文章

BUUCTF靶场[web][极客大挑战 2019]Http、[HCTF 2018]admin

目录   [web][极客大挑战 2019]Http 考点:Referer协议、UA协议、X-Forwarded-For协议 [web][HCTF 2018]admin 考点:弱密码字典爆破 四种方法:   [web][极客大挑战 2019]Http 考点:Referer协议、UA协议、X-Forwarded-For协议 访问环境 老规矩,我们先查看源代码

2019学习计划

工作三年了,第一年感觉是荒废的,第二年开始学习python,第三年开始自动化 感觉自己会的东西比较少,而且不够深入,流于表面 现制定一下今年大概的学习计划 需持续巩固加强:python、ui自动化、接口自动化、sql等 代码量需提升,敲的不够(重点) 学习: 1.移动端测试,appium等 2.前端知识系统整理学习  3.性能测试 4.docker入门,环境搭建 5.shell

GCDAsyncUdpSocket 使用时出现错误 Domain=NSPOSIXErrorDomain Code=13 Permission denied

完整的错误描述为: Domain=NSPOSIXErrorDomain Code=13 "Permission denied" UserInfo={NSLocalizedDescription=Permission denied, NSLocalizedFailureReason=Error in send() function.} 原始代码是这样的: clientBroadcast

最简单的使用JDBC[连接数据库] mysql 2019年3月18日

最极简版本的, 我们这里以mysql为例: 首先要创建maven工程, 需要引入jar包:,这里需要注意, 如果你安装的是mysql最新版本8以上的, 下面有些地方需要更改,具体就是mysql连接的url, 和5版本的不一样,具体解决请自行百度哈.这里只演示mysql5版本的? 依赖: <dependency>   <groupId>mysql</groupId>   <artifactId

最佳MyBatis 根据表结构自动生成代码, domain, dao, mapper 文件

摘要: 接触mybatis时间不是很长, 但是感觉也还容易上手, 好处发现也很多, 觉得还挺方便, 这段时间又学习一下MyBatis自动生成代码. 觉得在效率上更好了, 所以分享一下自动生成代码的步骤. 首先, 看看我的项目的包结构, 用的IDEA13.1,gradle包管理工具, ...其他的就没什么可说的; 今天, 主要讲 generator 里面的东西; mysql的jar包是

(php伪随机数生成)[GWCTF 2019]枯燥的抽奖

审核源码发现加载check.php,审计发现使用了mt_rand()函数,这个函数生成的值是伪随机的 参考下面这篇文章 PHP mt_rand安全杂谈及应用场景详解 - FreeBuf网络安全行业门户 kali里面输入下载工具 git clone https://github.com/openwall/php_mt_seed.git cd进去输入make后编译出的文件先

2019年2月17日

今天又重新看了一下输出第1500个丑数 在我错了八次之后发现要输出一个句号还要输出换行 接下来的两天应该进入复习阶段了。

National Contest for Private Universities (NCPU), 2019 E. Generalized Pascal's Triangle

编辑代码 2000ms 262144K Generalized Pascal's Triangle Pascal's triangle is a triangular array in which each number can be calculated by the sum of the two numbers directly above that number as shown i

Hinton等人最新研究:大幅提升模型准确率,标签平滑技术 2019-7-8

导读:损失函数对神经网络的训练有显著影响,也有很多学者人一直在探讨并寻找可以和损失函数一样使模型效果更好的函数。后来,Szegedy 等学者提出了标签平滑方法,该方法通过计算数据集中 hard target 的加权平均以及平均分布来计算交叉熵,有效提升了模型的准确率。近日,Hinton 团队等人在新研究论文《When Does Label Smoothing Help?》中,就尝试对标签平滑技术对

BM3D--Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering

系列文章目录 文章目录 系列文章目录前言稀疏三维变换域协同滤波图像去噪摘要1 引言2 分组和协作过滤A.分组B.按匹配分组C.协同过滤D.基于变换域收缩的协同过滤 3 算法结论 前言 论文地址 如果下载不了可以从 https://download.csdn.net/download/m0_70420861/89708940 获取 参考博客 :图像去噪算法:NL-Me