中文
相关论文

相关论文: Sliced Wasserstein Discrepancy in Disentangling Re…

200 篇论文

In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary and the Wasserstein metric. Our proposed sliced Wasserstein…

计算机视觉与模式识别 · 计算机科学 2019-03-12 Chen-Yu Lee , Tanmay Batra , Mohammad Haris Baig , Daniel Ulbricht

In this paper, we present DRANet, a network architecture that disentangles image representations and transfers the visual attributes in a latent space for unsupervised cross-domain adaptation. Unlike the existing domain adaptation methods…

计算机视觉与模式识别 · 计算机科学 2021-03-30 Seunghun Lee , Sunghyun Cho , Sunghoon Im

Graph-structured data can be found in numerous domains, yet the scarcity of labeled instances hinders its effective utilization of deep learning in many scenarios. Traditional unsupervised domain adaptation (UDA) strategies for graphs…

机器学习 · 计算机科学 2023-12-14 Mengxi Wu , Mohammad Rostami

Deep learning-based source dehazing methods trained on synthetic datasets have achieved remarkable performance but suffer from dramatic performance degradation on real hazy images due to domain shift. Although certain Domain Adaptation (DA)…

计算机视觉与模式识别 · 计算机科学 2022-07-15 Hu Yu , Jie Huang , Yajing Liu , Qi Zhu , Man Zhou , Feng Zhao

Deep neural networks have shown exceptional learning capability and generalizability in the source domain when massive labeled data is provided. However, the well-trained models often fail in the target domain due to the domain shift.…

计算机视觉与模式识别 · 计算机科学 2020-09-08 Chenyu You , Junlin Yang , Julius Chapiro , James S. Duncan

Domain shift poses a fundamental challenge in time series analysis, where models trained on source domain often fail dramatically when applied in target domain with different yet similar distributions. While current unsupervised domain…

机器学习 · 计算机科学 2025-08-07 Rongyao Cai , Ming Jin , Qingsong Wen , Kexin Zhang

Regularization techniques help prevent overfitting and therefore improve the ability of convolutional neural networks (CNNs) to generalize. One reason for overfitting is the complex co-adaptations among different parts of the network, which…

计算机视觉与模式识别 · 计算机科学 2024-09-30 Rinor Cakaj , Jens Mehnert , Bin Yang

Unsupervised Domain Adaptation (UDA) refers to the method that utilizes annotated source domain data and unlabeled target domain data to train a model capable of generalizing to the target domain data. Domain discrepancy leads to a…

计算机视觉与模式识别 · 计算机科学 2024-04-26 Ting Li , Jianshu Chao , Deyu An

Unsupervised domain adaptation (UDA) aims to address the domain-shift problem between a labeled source domain and an unlabeled target domain. Many efforts have been made to address the mismatch between the distributions of training and…

计算机视觉与模式识别 · 计算机科学 2020-07-28 Pingyang Dai , Peixian Chen , Qiong Wu , Xiaopeng Hong , Qixiang Ye , Qi Tian , Rongrong Ji

Domain adaptation aims at generalizing a high-performance learner on a target domain via utilizing the knowledge distilled from a source domain which has a different but related data distribution. One solution to domain adaptation is to…

机器学习 · 统计学 2018-03-12 Jian Shen , Yanru Qu , Weinan Zhang , Yong Yu

Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Beomseok Kang , Niluthpol Chowdhury Mithun , Abhinav Rajvanshi , Han-Pang Chiu , Supun Samarasekera

In single image super-resolution (SISR), given a low-resolution (LR) image, one wishes to find a high-resolution (HR) version of it which is both accurate and photo-realistic. Recently, it has been shown that there exists a fundamental…

图像与视频处理 · 电气工程与系统科学 2019-10-10 Xin Deng , Ren Yang , Mai Xu , Pier Luigi Dragotti

Accurate segmentation is a crucial step in medical image analysis and applying supervised machine learning to segment the organs or lesions has been substantiated effective. However, it is costly to perform data annotation that provides…

计算机视觉与模式识别 · 计算机科学 2021-10-29 Yunxiang Li , Jingxiong Li , Ruilong Dan , Shuai Wang , Kai Jin , Guodong Zeng , Jun Wang , Xiangji Pan , Qianni Zhang , Huiyu Zhou , Qun Jin , Li Wang , Yaqi Wang

Unsupervised Domain Adaptation (UDA) is crucial for reducing the need for extensive manual data annotation when training deep networks on point cloud data. A significant challenge of UDA lies in effectively bridging the domain gap. To…

计算机视觉与模式识别 · 计算机科学 2024-10-08 Mengxi Wu , Hao Huang , Yi Fang , Mohammad Rostami

Although unsupervised domain adaptation (UDA) is a promising direction to alleviate domain shift, they fall short of their supervised counterparts. In this work, we investigate relatively less explored semi-supervised domain adaptation…

计算机视觉与模式识别 · 计算机科学 2023-07-07 Hritam Basak , Zhaozheng Yin

Unsupervised domain adaptation (UDA) is essential for medical image segmentation, especially in cross-modality data scenarios. UDA aims to transfer knowledge from a labeled source domain to an unlabeled target domain, thereby reducing the…

图像与视频处理 · 电气工程与系统科学 2024-09-30 Hui Lin , Florian Schiffers , Santiago López-Tapia , Neda Tavakoli , Daniel Kim , Aggelos K. Katsaggelos

We present a novel approach for unsupervised domain adaptation (UDA) for natural images. A commonly-used objective for UDA schemes is to enhance domain alignment in representation space even if there is a domain shift in the input space.…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Ravi Kant Gupta , Shounak Das , Amit Sethi

Unsupervised domain adaptation (UDA) for semantic segmentation aims to adapt a segmentation model trained on the labeled source domain to the unlabeled target domain. Existing methods try to learn domain invariant features while suffering…

计算机视觉与模式识别 · 计算机科学 2021-07-28 Li Gao , Jing Zhang , Lefei Zhang , Dacheng Tao

The intricacy of rainy image contents often leads cutting-edge deraining models to image degradation including remnant rain, wrongly-removed details, and distorted appearance. Such degradation is further exacerbated when applying the models…

计算机视觉与模式识别 · 计算机科学 2023-02-15 Yiyang Shen , Mingqiang Wei , Sen Deng , Wenhan Yang , Yongzhen Wang , Xiao-Ping Zhang , Meng Wang , Jing Qin

Distribution matching is central to many vision and graphics tasks, where the widely used Wasserstein distance is too costly to compute for high dimensional distributions. The Sliced Wasserstein Distance (SWD) offers a scalable alternative,…

图形学 · 计算机科学 2025-10-02 Mark Boss , Andreas Engelhardt , Simon Donné , Varun Jampani
‹ 上一页 1 2 3 10 下一页 ›