而domain adaptation是一种transductive的风格迁移。 domain adaptation的分类: “unsupervised” domain adaptation : labeled source data + unlabeled target data “semi-supervised” domain adaptation :labeled source data+ some labeled target data are available “supervised” domain adaptation : labeled source an...
& Zheng, J. (2019). Temporal attentive alignment for large-scale video domain adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 6321-6330).http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Temporal_Attentive_Alignment_for_Large-Scale_Video_Domain...
Weak/semi-supervised domain adaptation: 无监督域自适应是特别有用的,因为标注目标域样本是劳动密集型和昂贵的目标检测任务。 但是,在某些情况下,可以为目标样本的子集获得边界框注释,或者提供指示类别存在/不存在的弱图像级注释。 在这种情况下,可以利用关于目标域的这些额外知识进一步提高目标域的性能。 对于弱监督...
Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives SuruchiKumari,PravendraSingh, inComputers in Biology and Medicine, 2024 Highlights • A survey of recent advances of deep unsuperviseddomain adaptation(UDA) formedical imaging. ...
Neural Unsupervised Domain Adaptation in NLP---A Surveydoi:10.18653/V1/2020.COLING-MAIN.603Alan RamponiBarbara PlankInternational Committee on Computational Linguistics
Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift Ruijia Xu1,†, Ziliang Chen1,†, Wangmeng Zuo2, Junjie Yan3, Liang Lin1,3∗ 1Sun Yat-sen University 2Harbin Institute of Technology 3SenseTime Research xurj3@mail2.sysu.edu.cn, c.ziliang@yahoo.com,...
Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation——CVPR2021,程序员大本营,技术文章内容聚合第一站。
Code Edit AlexisGuichemerreCode/survey_hist_w… 3 Tasks Edit Clustering Contrastive Learning Domain Adaptation Image Classification Self-Supervised Learning Unsupervised Domain Adaptation Datasets Edit ImageNet Office-31 VisDA-2017 Results from the Paper Edit Submit results from this paper to get...
* 题目: Domain-Guided Conditional Diffusion Model for Unsupervised Domain Adaptation* PDF: arxiv.org/abs/2309.1436* 作者: Yulong Zhang,Shuhao Chen,Weisen Jiang,Yu Zhang,Jiangang Lu,James T. Kwok* 其他: Work in progress 其他任务中的小样本学习 1篇 * 题目: ZiCo-BC: A Bias Corrected Zero-...
* Multi-Prompt Alignment for Multi-source Unsupervised Domain Adaptation* 链接: arxiv.org/abs/2209.1521* 作者: Haoran Chen,Zuxuan Wu,Yu-Gang Jiang* 摘要: 多数源无监督域适应(UDA)的大多数现有方法都依赖于共同的特征编码器来提取域不变特征。但是,学习这样的编码器涉及更新整个网络的参数,这使优化计算...