526互联

Unsupervised

Language Models are Unsupervised Multitask Learners

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！ OpenAI blog, 2019 ......
Unsupervised Multitask Language Learners Models

GPT-2 《Language Models are Unsupervised Multitask Learners》解读

背景 GPT1采用了pre-train + fine-tuning训练方式，也就是说为了适应不同的训练任务，模型还是需要在特定任务的数据集上微调，仍然存在较多人工干预的成本。GPT-2 想彻底解决这个问题，通过 zero-shot，在迁移到其他任务上的时候不需要额外的标注数据，也不需要额外的模型训练 ......
Unsupervised Multitask Language Learners Models

【PRC】鲁棒跨域伪标记和对比学习的无监督域自适应NIR-VIS人脸识别 Robust Cross-Domain Pseudo-Labeling and Contrastive Learning for Unsupervised Domain Adaptation NIR-VIS Face Recognition

【该文章为杨学长的文章，膜拜】 探索跨领域数据中的内在关系并学习领域不变表示 由于需要在低光照条件下实现24h的人脸识别，近红外加可见光的(NIR-VIS)人脸识别受到了更多的关注。但是数据标注是一个难点。该文章提出了Robust crossdomain Pseudo-labeling and Co ......
NIR-VIS Domain 人脸 Pseudo-Labeling Cross-Domain

[论文阅读] ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions

ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions Author：Zheng Li, Yue Zhao, Student Member Xiyang Hu, Nicola Bot ......
Distribution Unsupervised Cumulative Detection Empirical

Unsupervised Degradation Representation Learning f

Unsupervised Degradation Representation Learning for Blind Super-Resolution文献阅读 (2022.09.28)盲超分辨率的退化表征（向量）学习 摘要：大多数基于CNN的SR都是基于退化固定且可知这一假设。但是实际退化和假设不一 ......
Representation Unsupervised Degradation Learning

[论文阅读] Momentum contrast for unsupervised visual representation learning

# Momentum contrast for unsupervised visual representation learning ## Introduction 我们提出了动量对比（MoCo）作为一种构建具有对比损失的无监督学习的大型一致字典的方法（图1）。 我们将字典维护为数据样本队列：当前 ......
representation unsupervised Momentum contrast learning

论文解读（DEAL）《DEAL: An Unsupervised Domain Adaptive Framework for Graph-level Classification》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：DEAL: An Unsupervised Domain Adaptive Framework for Graph-level Classification论文作者：Nan Yin、Li Shen、Baop ......
DEAL Classification Unsupervised Graph-level Framework

论文解读（KD-UDA）《Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation论文作者：Yanping Fu, Yun Liu论文来源 ......
Distillation Unsupervised Progressive Adaptation Knowledge

论文解读（UDALM）《UDALM: Unsupervised Domain Adaptation through Language Modeling 》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：UDALM: Unsupervised Domain Adaptation through Language Modeling 论文作者：Constantinos Karouzos, Georgios Pa ......
UDALM Unsupervised Adaptation Language Modeling

论文解读（AAD）《Knowledge distillation for BERT unsupervised domain adaptation》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Knowledge distillation for BERT unsupervised domain adaptation论文作者：Minho Ryu、Geonseok Lee、Kichun Lee论文来 ......
distillation unsupervised adaptation Knowledge domain

论文解读（MCD）《Maximum Classifier Discrepancy for Unsupervised Domain Adaptation》

Note：[ wechat：Y466551 | 付费咨询，非诚勿扰 ] 论文信息 论文标题：Maximum Classifier Discrepancy for Unsupervised Domain Adaptation论文作者：Kuniaki Saito, Kohei Watanabe, Y. ......
Unsupervised Discrepancy Classifier Adaptation Maximum

论文解读（DWL）《Dynamic Weighted Learning for Unsupervised Domain Adaptation》

[ Wechat：Y466551 | 付费咨询，非诚勿扰 ] 论文信息 论文标题：Dynamic Weighted Learning for Unsupervised Domain Adaptation 论文作者：Jihong Ouyang、Zhengjie Zhang、Qingyi Meng论文来 ......
Unsupervised Adaptation Weighted Learning Dynamic

论文解读（）《Cluster Alignment with a Teacher for Unsupervised Domain Adaptation》

Note：[ wechat：Y466551 | 付费咨询，非诚勿扰 ] 论文信息 论文标题：Cluster Alignment with a Teacher for Unsupervised Domain Adaptation论文作者：Zhijie Deng, Yucen Luo, Jun Zhu论 ......
Unsupervised Adaptation Alignment Cluster Teacher

Unsupervised Learning of Depth and Ego-Motion from Video(CVPR2017)论文阅读

深度估计问题 从输入的单目或双目图像，计算图像物体与摄像头之间距离（输出距离图），双目的距离估计应该是比较成熟和完善，但往单目上考虑主要还是成本的问题，所以做好单目的深度估计有一定的意义。单目的意思是只有一个摄像头，同一个时间点只有一张图片。就象你闭上一只眼睛，只用一只眼睛看这个世界的事物一样，距离 ......
Unsupervised Ego-Motion Learning Motion 论文

4.5 Unsupervised Learning: Word Embedding

# 1. Introduction(引入) 词嵌入(word embedding)是降维算法(Dimension Reduction)的典型应用. 最经典的做法就是1-of-N Encoding,它指的就是每一个字都是以向量来表示,只有在自己所属的那个字词索引上为1,其余为0,因此如果世界上的英文字 ......
Unsupervised Embedding Learning Word 4.5

[论文阅读] DGFont++ Robust Deformable Generative Networks for Unsupervised Font Generation

## Pre title: DGFont++: Robust Deformable Generative Networks for Unsupervised Font Generation accepted: Arxiv 2022 paper: https://arxiv.org/abs/2212. ......
Unsupervised Deformable Generative Generation Networks

DYNAMICS-AWARE UNSUPERVISED DISCOVERY OF SKILLS

**发表时间：**2020（ICLR2020） **文章要点：**这篇文章提出了一个无监督的model-based的学习算法Dynamics-Aware Discovery of Skills (DADS)，可以同时发现可预测的行为以及学习他们的dynamics。然后对于新任务，可以直接用zero- ......
DYNAMICS-AWARE UNSUPERVISED DISCOVERY DYNAMICS SKILLS

迁移学习（VMT）《Virtual Mixup Training for Unsupervised Domain Adaptation》

论文信息 论文标题：Virtual Mixup Training for Unsupervised Domain Adaptation论文作者：Takeru Miyato, S. Maeda, Masanori Koyama, S. Ishii论文来源：2019 CVPR论文地址：download  ......
Unsupervised Adaptation Training Virtual Domain

迁移学习（MEnsA）《MEnsA: Mix-up Ensemble Average for Unsupervised Multi Target Domain Adaptation on 3D Point Clouds》

论文信息 论文标题：MEnsA: Mix-up Ensemble Average for Unsupervised Multi Target Domain Adaptation on 3D Point Clouds论文作者：Ashish Sinha, Jonghyun Choi论文来源：2023 C ......
MEnsA Unsupervised Adaptation Ensemble Average

猛读论文13 |【CVPR 2022 UDA】Unleashing Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification

动机 解决（1）对比学习管道中的增强通常会扭曲人物图像中的判别线索（2）细粒度的局部特征人物图像尚未得到充分探索。 思路 方法 ......
Re-Identification Intra-Identity Identification Regularization Pre-Training

迁移学习（PAT）《Pairwise Adversarial Training for Unsupervised Class-imbalanced Domain Adaptation》

论文信息 论文标题：Pairwise Adversarial Training for Unsupervised Class-imbalanced Domain Adaptation论文作者：Weili Shi, Ronghang Zhu, Sheng Li论文来源：KDD 2022论文地址：dow ......
Class-imbalanced Unsupervised Adversarial Adaptation imbalanced

迁移学习《Efficient and Robust Pseudo-Labeling for Unsupervised Domain Adaptation》

论文信息 论文标题：Efficient and Robust Pseudo-Labeling for Unsupervised Domain Adaptation论文作者：Hochang Rhee、Nam Ik Cho论文来源：2019——ICML论文地址：download 论文代码：downloa ......
Pseudo-Labeling Unsupervised Adaptation Efficient Labeling

迁移学习《Asymmetric Tri-training for Unsupervised Domain Adaptation》

论文信息 论文标题：Asymmetric Tri-training for Unsupervised Domain Adaptation论文作者：Kuniaki Saito, Y. Ushiku, T. Harada论文来源：27 February 2017——ICML论文地址：download 论 ......
Tri-training Unsupervised Asymmetric Adaptation training

迁移学习（TSRP）《Improving Pseudo Labels With Intra-Class Similarity for Unsupervised Domain Adaptation》

论文信息 论文标题：Improving Pseudo Labels With Intra-Class Similarity for Unsupervised Domain Adaptation论文作者：Jie Wang, Xiaoli Zhang论文来源：论文地址：download 论文代码：dow ......
Unsupervised Intra-Class Adaptation Similarity Improving

迁移学习（DCCL）《Domain Confused Contrastive Learning for Unsupervised Domain Adaptation》

论文信息 论文标题：Domain Confused Contrastive Learning for Unsupervised Domain Adaptation论文作者：Quanyu Long, Tianze Luo, Wenya Wang and Sinno Jialin Pan论文来源：NAA ......
Domain Unsupervised Contrastive Adaptation Confused

【论文精读 - DDPM】Deep Unsupervised Learning using Nonequilibrium Thermodynamics

数学推导【转载】 数学推导过程来自苏剑林大神的《生成扩散模型漫谈》系列，感谢苏神的无私奉献，让我这样数学功底不好的人也能领略这个当下最为火爆的模型的精髓。 系列中有部分步骤，一眼看过去可能有些费解，所以这里稍微做了展开，作为自己的笔记用。 通俗解释：DDPM=拆楼+建楼 生成模型实际上就是：随机噪声 ......
Nonequilibrium Thermodynamics Unsupervised Learning 论文

Debiased Contrastive Learning of Unsupervised Sentence Representations 论文精读

ACL2022-long paper 原文地址 1. 介绍(Introduction) 问题: 由PLM编码得到的句子表示在方向上分布不均匀, 在向量空间中占据一个狭窄的锥形区域, 这在很大程度上限制了它们的表达能力. 已有的解决办法: 对比学习. 对于一个原句, 构造他的正例(语义相似的句子)和负 ......
Representations Unsupervised Contrastive Debiased Learning

迁移学习（JDDA） 《Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation》

论文信息 论文标题：Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation论文作者：Chao Chen , Zhihong Chen , Boyuan Jia ......
domain discriminative unsupervised adaptation alignment

迁移学习（IIMT）——《Improve Unsupervised Domain Adaptation with Mixup Training》

论文信息 论文标题：Improve Unsupervised Domain Adaptation with Mixup Training论文作者：Shen Yan, Huan Song, Nanxiang Li, Lincan Zou, Liu Ren论文来源：arxiv 2020论文地址：down ......
Unsupervised Adaptation Training Improve Domain

迁移学习（DANN）《Unsupervised Domain Adaptation by Backpropagation》

论文信息 论文标题：Domain-Adversarial Training of Neural Networks论文作者：Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain论文来源：JMLR 2016论文地址：download ......
Backpropagation Unsupervised Adaptation Domain DANN
共33篇  :1/2页 首页上一页1下一页尾页