English
Related papers

Related papers: Domain Generalization Guided by Large-Scale Pre-Tr…

200 papers

Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on…

Computation and Language · Computer Science 2023-10-09 Zhengxiang Shi , Aldo Lipani

For modern artificial intelligence (AI) applications such as large language models (LLMs), the training paradigm has recently shifted to pre-training followed by fine-tuning. Furthermore, owing to dwindling open repositories of data and…

Machine Learning · Computer Science 2025-12-02 Haifeng Wen , Hong Xing , Osvaldo Simeone

To adapt effectively to dynamic real-world environments, intelligent systems must continually acquire new skills while generalizing them to diverse, unseen scenarios. Here, we introduce a novel and realistic setting named domain…

Machine Learning · Computer Science 2025-10-21 Hongwei Yan , Guanglong Sun , Zhiqi Kang , Yi Zhong , Liyuan Wang

Existing deep learning methods for remote sensing image fusion often suffer from poor generalization when applied to unseen datasets due to the limited availability of real training data and the domain gap between different satellite…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Yongchuan Cui , Peng Liu , Yi Zeng

Domain generalisation (DG) methods address the problem of domain shift, when there is a mismatch between the distributions of training and target domains. Data augmentation approaches have emerged as a promising alternative for DG. However,…

Machine Learning · Computer Science 2020-12-29 Hoang Son Le , Rini Akmeliawati , Gustavo Carneiro

Machine learning typically relies on the assumption that training and testing distributions are identical and that data is centrally stored for training and testing. However, in real-world scenarios, distributions may differ significantly…

Machine Learning · Computer Science 2025-08-22 Ying Li , Xingwei Wang , Rongfei Zeng , Praveen Kumar Donta , Ilir Murturi , Min Huang , Schahram Dustdar

With the goal of directly generalizing trained model to unseen target domains, domain generalization (DG), a newly proposed learning paradigm, has attracted considerable attention. Previous DG models usually require a sufficient quantity of…

Computer Vision and Pattern Recognition · Computer Science 2022-08-18 Ruiqi Wang , Lei Qi , Yinghuan Shi , Yang Gao

When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…

Computation and Language · Computer Science 2025-05-26 Xiang Liu , Zhaoxiang Liu , Peng Wang , Kohou Wang , Huan Hu , Kai Wang , Shiguo Lian

Machine learning models fail to perform when facing out-of-distribution (OOD) domains, a challenging task known as domain generalization (DG). In this work, we develop a novel DG training strategy, we call PGrad, to learn a robust gradient…

Machine Learning · Computer Science 2023-05-03 Zhe Wang , Jake Grigsby , Yanjun Qi

Large-scale pre-trained vision-language models like CLIP have demonstrated impressive performance across various tasks, and exhibit remarkable zero-shot generalization capability, while they are also vulnerable to imperceptible adversarial…

Computer Vision and Pattern Recognition · Computer Science 2024-04-11 Sibo Wang , Jie Zhang , Zheng Yuan , Shiguang Shan

Domain Generalization (DG) aims to resolve distribution shifts between source and target domains, and current DG methods are default to the setting that data from source and target domains share identical categories. Nevertheless, there…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Zining Chen , Weiqiu Wang , Zhicheng Zhao , Fei Su , Aidong Men , Hongying Meng

Domain Generalization (DG) aims to train models that can effectively generalize to unseen domains. However, in the context of Federated Learning (FL), where clients collaboratively train a model without directly sharing their data, most…

Machine Learning · Computer Science 2024-11-27 Xinpeng Wang , Yongxin Guo , Xiaoying Tang

Domain adaption (DA) and domain generalization (DG) are two closely related methods which are both concerned with the task of assigning labels to an unlabeled data set. The only dissimilarity between these approaches is that DA can access…

Computer Vision and Pattern Recognition · Computer Science 2018-12-27 Mohammad Mahfujur Rahman , Clinton Fookes , Mahsa Baktashmotlagh , Sridha Sridharan

Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various tasks, recent studies have observed challenges in the…

Machine Learning · Computer Science 2024-06-21 Yuji Roh , Qingyun Liu , Huan Gui , Zhe Yuan , Yujin Tang , Steven Euijong Whang , Liang Liu , Shuchao Bi , Lichan Hong , Ed H. Chi , Zhe Zhao

Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being supervised, SFT is inherently limited by its generative…

Computation and Language · Computer Science 2025-07-25 Siqi Guo , Ilgee Hong , Vicente Balmaseda , Changlong Yu , Liang Qiu , Xin Liu , Haoming Jiang , Tuo Zhao , Tianbao Yang

During the pretraining phase, large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora. Nevertheless, in later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the…

Computation and Language · Computer Science 2024-10-10 Bozhou Li , Hao Liang , Yang Li , Fangcheng Fu , Hongzhi Yin , Conghui He , Wentao Zhang

Large pretrained language models (PLMs) are often domain- or task-adapted via fine-tuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and…

Computation and Language · Computer Science 2022-07-11 Zejiang Hou , Julian Salazar , George Polovets

Recently, much exertion has been paid to design graph self-supervised methods to obtain generalized pre-trained models, and adapt pre-trained models onto downstream tasks through fine-tuning. However, there exists an inherent gap between…

Machine Learning · Computer Science 2023-08-16 Yun Zhu , Jianhao Guo , Siliang Tang

In the field of object detection, domain generalisation (DG) aims to ensure robust performance across diverse and unseen target domains by learning the robust domain-invariant features corresponding to the objects of interest across…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Shuvam Jena , Sushmetha Sumathi Rajendran , Karthik Seemakurthy , Sasithradevi A , Vijayalakshmi M , Prakash Poornachari

Prior feature transformation based approaches to Unsupervised Domain Adaptation (UDA) employ the deep features extracted by pre-trained deep models without fine-tuning them on the specific source or target domain data for a particular…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Qian Wang , Toby P. Breckon