domain adaptation论文记录

1 An Intelligent Fault Diagnosis Method Based on Domain Adaptation and Its Application for Bearings Under Polytropic Working Conditions

创新点:
(1) a domain adaptation method based on multi-scale mixed domain feature is proposed.
(2) adaptive domain adaptation(同时考虑条件概率和边缘概率)
(3)A feature optimizer based on GS_XGBoost is proposed, which not only reduces the dimension of features and eliminates redundant information, but also gives the importance ranking of features to understand the contribution of different features for diagnosis and recognition, and then selects sensitive feature subsets to diagnosis
在这里插入图片描述

2 Deep Learning-Based Partial Domain Adaptation Method on Intelligent Machinery Fault Diagnostics

创新点
(1) address the partial domain adaptation
(2) The conditional data alignment and unsupervised prediction consistency schemes are proposed to achieve partial domain adaptation.
在这里插入图片描述

3 Adversarial domain-invariant generalization a generic domain-regressive framework for bearing fault diagnosis under unseen conditions

创新点:
(1) 提出了domain generalization解决unseen target问题
在这里插入图片描述
(2)Customized IN and SN strategies achieve cross-domain feature normalization to promote domain generalizability
(3)an adaptive weight strategy achieves weight self-learning during multitask learning to improve performance.(自适应调整各损失的相对权重,解决手动调参的问题)

4 Adversarial Multiple-Target Domain Adaptation for Fault Classification(开源)

创新点:
(1) 解决单源域多目标域问题
在这里插入图片描述
在这里插入图片描述

5 Adversarial Entropy Optimization for Unsupervised Domain Adaptation

创新点
在这里插入图片描述
当特征来自于源域或目标域的独立分布时,最小化熵损失,当特征来自于目标域和源域的组合分布时,最大化熵损失。

6 Deep Coupled Joint Distribution Adaptation Network: A Method for Intelligent Fault Diagnosis Between Artificial and Real Damages

创新点:
在这里插入图片描述
(1)在提取特征时,源域和目标域的网络结构不一样,用一个正则项来联系两个网络;
(2)同时考虑条件概率分布和边缘概率分布。

7 Conditional Adversarial Domain Adaptation With Discrimination Embedding for Locomotive Fault Diagnosis

创新点:
在这里插入图片描述
(1)Instead of inputting features of the source and target domains into the domain classifier, the multilinear map of features and label predictions are inputted into the domain classifier
(2)CADA

8 Extreme Learning Machine Based on Maximum Weighted Mean Discrepancy for Unsupervised Domain Adaptation

创新点:
在这里插入图片描述
(1)考虑每一个样本的权重;
(2)引入超极限学习

9 Adaptive Graph Adversarial Networks for Partial Domain Adaptation

在这里插入图片描述
创新点:
(1)针对partial domain adaptation问题
(2)we propose Adaptive Graph Adversarial Networks (AGAN) consisting of two specialized modules. The adaptive class-relational graph module is designed to utilize the intra-and inter-domain structures through adaptive feature propagation. Complementarily, the sample-level commonness predictor computes a commonness score of each sample.

### 半监督学习的研究论文 半监督学习是一种利用少量标注数据和大量未标注数据来提高模型性能的学习方法。这种方法在实际应用中非常有用,尤其是在获取标注数据成本较高的情况下。 #### 关于对比学习的应用 对比学习可以应用于有监督和无监督设置,在处理无监督数据时尤为有效[^1]。这种技术已经成为自监督学习中最强大的方法之一。 #### 图卷积网络的半监督分类 一篇重要的研究论文《Semi-supervised Classification with Graph Convolutional Networks》(2017年发布),探讨了图卷积网络如何用于节点级别的半监督分类任务[^2]。该论文提出了基于谱图理论的方法,并展示了其在多个标准数据集上的优越表现。 以下是几篇值得查阅的相关学术论文: 1. **Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks** 这篇文章介绍了一种简单高效的伪标签方法,适用于深度神经网络中的半监督学习场景。通过为未标记的数据分配伪标签并将其纳入训练过程,显著提高了模型的表现。 2. **Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results** 此论文提出了一种名为“均值教师”的框架,它通过对权重进行平均化操作以生成一致性目标,从而改进了半监督深度学习的结果。 3. **Unsupervised Domain Adaptation by Backpropagation** 虽然主要关注域适应问题,但此文章也涉及到了半监督学习的思想,特别是跨不同领域之间的特征对齐策略。 4. **Temporal Ensembling for Semi-Supervised Learning** 提出了时间集成法作为解决半监督图像分类的一种新途径。通过维护每个样本预测分布的历史记录,增强了模型鲁棒性和准确性。 ```python import requests def fetch_paper(paper_url): response = requests.get(paper_url) if response.status_code == 200: return "Paper fetched successfully." else: return f"Failed to fetch paper. Status code {response.status_code}." paper_urls = [ "https://arxiv.org/pdf/1609.02907.pdf", # GCN Paper "https://arxiv.org/pdf/1308.5857v2.pdf", # Pseudo Label Paper "https://arxiv.org/pdf/1703.01780.pdf", # Mean Teacher Paper ] for url in paper_urls: print(fetch_paper(url)) ```
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值