中文
相关论文

相关论文: The Role of Embedding Complexity in Domain-invaria…

200 篇论文

One recent research demonstrated successful application of the label alignment property for unsupervised domain adaptation in a linear regression settings. Instead of regularizing representation learning to be domain invariant, the research…

机器学习 · 计算机科学 2025-03-13 Xuanrui Zeng

Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching…

机器学习 · 计算机科学 2018-11-20 Jun Wen , Risheng Liu , Nenggan Zheng , Qian Zheng , Zhefeng Gong , Junsong Yuan

Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several recent methods use multiple datasets to train models to extract domain-invariant features, hoping to generalize…

机器学习 · 计算机科学 2021-05-19 Mattia Segu , Alessio Tonioni , Federico Tombari

The recent success of deep neural networks relies on massive amounts of labeled data. For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. In this paper, we propose a…

机器学习 · 计算机科学 2017-02-17 Mingsheng Long , Han Zhu , Jianmin Wang , Michael I. Jordan

The goal of domain adaptation is to adapt models learned on a source domain to a particular target domain. Most methods for unsupervised domain adaptation proposed in the literature to date, assume that the set of classes present in the…

计算机视觉与模式识别 · 计算机科学 2016-03-29 Ayush Mittal , Anant Raj , Vinay P. Namboodiri , Tinne Tuytelaars

Convolutional neural networks trained on publicly available medical imaging datasets (source domain) rarely generalise to different scanners or acquisition protocols (target domain). This motivates the active field of domain adaptation.…

图像与视频处理 · 电气工程与系统科学 2020-10-06 Thomas Varsavsky , Mauricio Orbes-Arteaga , Carole H. Sudre , Mark S. Graham , Parashkev Nachev , M. Jorge Cardoso

In recent years, deep neural networks have emerged as a dominant machine learning tool for a wide variety of application domains. However, training a deep neural network requires a large amount of labeled data, which is an expensive process…

计算机视觉与模式识别 · 计算机科学 2017-06-26 Hemanth Venkateswara , Jose Eusebio , Shayok Chakraborty , Sethuraman Panchanathan

This paper addresses unsupervised domain adaptation, the setting where labeled training data is available on a source domain, but the goal is to have good performance on a target domain with only unlabeled data. Like much of previous work,…

机器学习 · 计算机科学 2019-10-01 Yu Sun , Eric Tzeng , Trevor Darrell , Alexei A. Efros

We propose a novel unsupervised domain adaptation framework based on domain-specific batch normalization in deep neural networks. We aim to adapt to both domains by specializing batch normalization layers in convolutional neural networks…

机器学习 · 计算机科学 2019-06-11 Woong-Gi Chang , Tackgeun You , Seonguk Seo , Suha Kwak , Bohyung Han

When machine learning models are deployed on a test distribution different from the training distribution, they can perform poorly, but overestimate their performance. In this work, we aim to better estimate a model's performance under…

机器学习 · 计算机科学 2020-07-08 Ching-Yao Chuang , Antonio Torralba , Stefanie Jegelka

The problem of domain adaptation (DA) deals with adapting classifier models trained on one data distribution to different data distributions. In this paper, we introduce the Nonlinear Embedding Transform (NET) for unsupervised DA by…

计算机视觉与模式识别 · 计算机科学 2017-06-26 Hemanth Venkateswara , Shayok Chakraborty , Sethuraman Panchanathan

A central problem in unsupervised domain adaptation is determining what to transfer from labeled source domains to an unlabeled target domain. To handle high-dimensional observations (e.g., images), a line of approaches use deep learning to…

机器学习 · 计算机科学 2026-04-28 Ignavier Ng , Yan Li , Zijian Li , Yujia Zheng , Guangyi Chen , Kun Zhang

We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not…

机器学习 · 计算机科学 2019-05-28 Safa Cicek , Stefano Soatto

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised…

计算机视觉与模式识别 · 计算机科学 2025-10-24 Ziyu Ye , Chen Ju , Chaofan Ma , Xiaoyun Zhang

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two…

机器学习 · 计算机科学 2019-11-20 Qian Wang , Toby P. Breckon

Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision.…

计算机视觉与模式识别 · 计算机科学 2020-03-31 Wenchao Du , Hu Chen , Hongyu Yang

Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source…

We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation…

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…

机器学习 · 计算机科学 2021-06-30 Yuntao Du , Yinghao Chen , Fengli Cui , Xiaowen Zhang , Chongjun Wang

Compared with shallow domain adaptation, recent progress in deep domain adaptation has shown that it can achieve higher predictive performance and stronger capacity to tackle structural data (e.g., image and sequential data). The underlying…

机器学习 · 计算机科学 2019-06-21 Trung Le , Khanh Nguyen , Nhat Ho , Hung Bui , Dinh Phung