中文
相关论文

相关论文: Contrastive ACE: Domain Generalization Through Ali…

200 篇论文

Domain Generalization (DG) aims to learn a model that can generalize well to unseen target domains from a set of source domains. With the idea of invariant causal mechanism, a lot of efforts have been put into learning robust causal effects…

计算机视觉与模式识别 · 计算机科学 2022-10-07 Qiaowei Miao , Junkun Yuan , Kun Kuang

Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain…

机器学习 · 计算机科学 2022-06-17 Wenyu Zhang , Mohamed Ragab , Chuan-Sheng Foo

Machine learning models rely on various assumptions to attain high accuracy. One of the preliminary assumptions of these models is the independent and identical distribution, which suggests that the train and test data are sampled from the…

机器学习 · 计算机科学 2022-11-08 Paras Sheth , Raha Moraffah , K. Selçuk Candan , Adrienne Raglin , Huan Liu

Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true…

机器学习 · 统计学 2018-09-25 Mateo Rojas-Carulla , Bernhard Schölkopf , Richard Turner , Jonas Peters

Domain generalization aims to apply knowledge gained from multiple labeled source domains to unseen target domains. The main difficulty comes from the dataset bias: training data and test data have different distributions, and the training…

机器学习 · 计算机科学 2018-07-24 Ya Li , Mingming Gong , Xinmei Tian , Tongliang Liu , Dacheng Tao

Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all…

机器学习 · 计算机科学 2022-02-16 A. Tuan Nguyen , Toan Tran , Yarin Gal , Atılım Güneş Baydin

Domain generalization aims to enhance the model robustness against domain shift without accessing the target domain. Since the available source domains for training are limited, recent approaches focus on generating samples of novel…

计算机视觉与模式识别 · 计算机科学 2021-08-20 Seogkyu Jeon , Kibeom Hong , Pilhyeon Lee , Jewook Lee , Hyeran Byun

We introduce Domain-specific Masks for Generalization, a model for improving both in-domain and out-of-domain generalization performance. For domain generalization, the goal is to learn from a set of source domains to produce a single model…

计算机视觉与模式识别 · 计算机科学 2020-09-01 Prithvijit Chattopadhyay , Yogesh Balaji , Judy Hoffman

Generalizing knowledge to unseen domains, where data and labels are unavailable, is crucial for machine learning models. We tackle the domain generalization problem to learn from multiple source domains and generalize to a target domain…

计算机视觉与模式识别 · 计算机科学 2022-04-06 Fan Zhou , Zhuqing Jiang , Changjian Shui , Boyu Wang , Brahim Chaib-draa

This paper investigates domain generalization: How to take knowledge acquired from an arbitrary number of related domains and apply it to previously unseen domains? We propose Domain-Invariant Component Analysis (DICA), a kernel-based…

机器学习 · 统计学 2013-01-11 Krikamol Muandet , David Balduzzi , Bernhard Schölkopf

Domain generalization (DG) focuses on transferring domain-invariant knowledge from multiple source domains (available at train time) to an, a priori, unseen target domain(s). This requires a class to be expressed in multiple domains for the…

机器学习 · 计算机科学 2023-06-02 Kimathi Kaai , Saad Hossain , Sirisha Rambhatla

Deep neural networks can obtain impressive performance on various tasks under the assumption that their training domain is identical to their target domain. Performance can drop dramatically when this assumption does not hold. One…

机器学习 · 计算机科学 2024-10-10 Gaël Gendron , Michael Witbrock , Gillian Dobbie

Domain generalization approaches aim to learn a domain invariant prediction model for unknown target domains from multiple training source domains with different distributions. Significant efforts have recently been committed to broad…

计算机视觉与模式识别 · 计算机科学 2021-08-23 Mohammad Mahfujur Rahman , Clinton Fookes , Sridha Sridharan

Domain adaption has been widely adapted for cross-domain sentiment analysis to transfer knowledge from the source domain to the target domain. Whereas, most methods are proposed under the assumption that the target (test) domain is known,…

计算与语言 · 计算机科学 2024-02-23 Siyin Wang , Jie Zhou , Qin Chen , Qi Zhang , Tao Gui , Xuanjing Huang

An important goal common to domain adaptation and causal inference is to make accurate predictions when the distributions for the source (or training) domain(s) and target (or test) domain(s) differ. In many cases, these different…

机器学习 · 计算机科学 2022-08-31 Sara Magliacane , Thijs van Ommen , Tom Claassen , Stephan Bongers , Philip Versteeg , Joris M. Mooij

Domain generalization (DG) aims to incorporate knowledge from multiple source domains into a single model that could generalize well on unseen target domains. This problem is ubiquitous in practice since the distributions of the target data…

机器学习 · 统计学 2019-07-26 Shoubo Hu , Kun Zhang , Zhitang Chen , Laiwan Chan

Domain generalization models aim to learn cross-domain knowledge from source domain data, to improve performance on unknown target domains. Recent research has demonstrated that diverse and rich source domain samples can enhance domain…

机器学习 · 计算机科学 2024-03-12 Jianting Chen , Ling Ding , Yunxiao Yang , Zaiyuan Di , Yang Xiang

Traditional domain generalization methods often rely on domain alignment to reduce inter-domain distribution differences and learn domain-invariant representations. However, domain shifts are inherently difficult to eliminate, which limits…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Yuheng Xu , Taiping Zhang

The problem of domain generalization concerns learning predictive models that are robust to distribution shifts when deployed in new, previously unseen environments. Existing methods typically require labeled data from multiple training…

Real-world classification problems must contend with domain shift, the (potential) mismatch between the domain where a model is deployed and the domain(s) where the training data was gathered. Methods to handle such problems must specify…

机器学习 · 计算机科学 2022-07-05 Yibo Jiang , Victor Veitch
‹ 上一页 1 2 3 10 下一页 ›