中文
相关论文

相关论文: Is Large-Scale Pretraining the Secret to Good Doma…

200 篇论文

The domain shift between training and testing data presents a significant challenge for training generalizable deep learning models. As a consequence, the performance of models trained with the independent and identically distributed…

计算机视觉与模式识别 · 计算机科学 2023-09-19 Aleksandr Matsun , Dana O. Mohamed , Sharon Chokuwa , Muhammad Ridzuan , Mohammad Yaqub

Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent work observe that the popular adversarial approach of…

机器学习 · 统计学 2020-01-06 Shen Yan , Huan Song , Nanxiang Li , Lincan Zou , Liu Ren

Unsupervised domain adaptation leverages abundant labeled data from various source domains to generalize onto unlabeled target data. Prior research has primarily focused on learning domain-invariant features across the source and target…

计算与语言 · 计算机科学 2025-03-10 Jie He , Wendi Zhou , Xiang Lorraine Li , Jeff Z. Pan

Domain adaptive semantic segmentation is recognized as a promising technique to alleviate the domain shift between the labeled source domain and the unlabeled target domain in many real-world applications, such as automatic pilot. However,…

计算机视觉与模式识别 · 计算机科学 2021-10-14 Fuming You , Jingjing Li , Lei Zhu , Ke Lu , Zhi Chen , Zi Huang

Data-driven machine learning (ML) is promoted as one potential technology to be used in next-generations wireless systems. This led to a large body of research work that applies ML techniques to solve problems in different layers of the…

机器学习 · 计算机科学 2023-03-15 Mohamed Akrout , Amal Feriani , Faouzi Bellili , Amine Mezghani , Ekram Hossain

We propose a novel approach for domain generalisation (DG) leveraging risk distributions to characterise domains, thereby achieving domain invariance. In our findings, risk distributions effectively highlight differences between training…

机器学习 · 计算机科学 2023-10-31 Toan Nguyen , Kien Do , Bao Duong , Thin Nguyen

Domain generalization on graphs aims to develop models with robust generalization capabilities, ensuring effective performance on the testing set despite disparities between testing and training distributions. However, existing methods…

机器学习 · 计算机科学 2024-11-21 Qin Tian , Chen Zhao , Minglai Shao , Wenjun Wang , Yujie Lin , Dong Li

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…

计算机视觉与模式识别 · 计算机科学 2019-10-31 Qi Dou , Daniel C. Castro , Konstantinos Kamnitsas , Ben Glocker

Model generalizability to unseen datasets, concerned with in-the-wild robustness, is less studied for indoor single-image depth prediction. We leverage gradient-based meta-learning for higher generalizability on zero-shot cross-dataset…

计算机视觉与模式识别 · 计算机科学 2024-01-31 Cho-Ying Wu , Yiqi Zhong , Junying Wang , Ulrich Neumann

As deep learning-based systems have become an integral part of everyday life, limitations in their generalization ability have begun to emerge. Machine learning algorithms typically rely on the i.i.d. assumption, meaning that their training…

计算机视觉与模式识别 · 计算机科学 2024-07-25 Aristotelis Ballas , Christos Diou

Domain generalization (DG) aims to improve the generalization ability of the model trained on several known training domains over unseen test domains. Previous work has shown that self-supervised contrastive pre-training improves the…

机器学习 · 计算机科学 2024-01-09 Chujie Zhao , Tianren Zhang , Feng Chen

As machine learning evolves, domain generalization (DG) and domain adaptation (DA) have become crucial for enhancing model robustness across diverse environments. Contrastive Language-Image Pretraining (CLIP) plays a significant role in…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Jindong Li , Yongguang Li , Yali Fu , Jiahong Liu , Yixin Liu , Menglin Yang , Irwin King

Medical imaging datasets usually exhibit domain shift due to the variations of scanner vendors, imaging protocols, etc. This raises the concern about the generalization capacity of machine learning models. Domain generalization (DG), which…

计算机视觉与模式识别 · 计算机科学 2021-06-15 Chenxin Li , Qi Qi , Xinghao Ding , Yue Huang , Dong Liang , Yizhou Yu

The objective of Domain Generalization (DG) is to devise algorithms and models capable of achieving high performance on previously unseen test distributions. In the pursuit of this objective, average measure has been employed as the…

机器学习 · 计算机科学 2024-06-04 Duhun Hwang , Suhyun Kang , Moonjung Eo , Jimyeong Kim , Wonjong Rhee

Domain generalization (DG) is about training models that generalize well under domain shift. Previous research on DG has been conducted mostly in single-source or multi-source settings. In this paper, we consider a third, lesser-known…

机器学习 · 计算机科学 2024-06-13 Han Gao , Kaican Li , Weiyan Xie , Zhi Lin , Yongxiang Huang , Luning Wang , Caleb Chen Cao , Nevin L. Zhang

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

In practical machine learning settings, the data on which a model must make predictions often come from a different distribution than the data it was trained on. Here, we investigate the problem of unsupervised multi-source domain…

机器学习 · 计算机科学 2020-09-17 Dustin Wright , Isabelle Augenstein

Visual recognition systems are meant to work in the real world. For this to happen, they must work robustly in any visual domain, and not only on the data used during training. Within this context, a very realistic scenario deals with…

计算机视觉与模式识别 · 计算机科学 2018-10-01 Antonio D'Innocente , Barbara Caputo

Domain generalization aims to solve the challenge of Out-of-Distribution (OOD) generalization by leveraging common knowledge learned from multiple training domains to generalize to unseen test domains. To accurately evaluate the OOD…

机器学习 · 计算机科学 2024-03-26 Han Yu , Xingxuan Zhang , Renzhe Xu , Jiashuo Liu , Yue He , Peng Cui

Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID), which trains the model using labels from the source domain alone, and then directly adopts the trained model to the target domain without…

信息检索 · 计算机科学 2020-07-28 Peixian Chen , Pingyang Dai , Jianzhuang Liu , Feng Zheng , Qi Tian , Rongrong Ji