GitHub is where people build software. More than 100 million people use GitHub to discover, fork, and contribute to over 420 million projects.
For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statistics. However, the optimization objective of such domain alignment is generally not...
Existing unsupervised domain adaptation methods based on adversarial learning have achieved good performance in several medical imaging tasks. However, these methods focus only on global distribution adaptation and ignore distribution constraints at the category level, which would lead to sub-optimal ...
我们的方法的源代码可在以下链接获取:https://github.com/christinecui/CPH。 Title:Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation Accept:AAAI2024 摘要:最近,尽管大型预训练视觉-语言模型(VLMs)在广泛的下游任务上取得了前所未有的成功,但现实世界中的无监督领域自适应(UDA)问题仍未得到充分...
论文代码:https://github.com/fungtion/DANN 问题描述:深度学习的模型在source domain数据集上训练的很好(90%左右),但是迁移到target domain的效果就很差(54%左右),这种现象叫做domain shift。 Target Domain的图片是无标签 《Unsupervised domain Adaptation by Backpropagation》这篇论文发表于2015 ICML,目前引用量已...
Unsupervised Domain Adaptation by Backpropagation. Contribute to se-kami/dann development by creating an account on GitHub.
Title: Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation Code: https://github.com/TL-UESTC/DAMP. Accept: CVPR 2024 Abstract: 传统的无监督域适应方法(UDA)力求最小化域间的分布差异,…
Enhanced Transport Distance for Unsupervised Domain Adaptation (ETD) This is the pytorch demo code for Enhanced Transport Distance for Unsupervised Domain Adaptation (ETD) (CVPR 2020)Requirementspython 3.7 torch 1.2.0 torchvision 0.4.0 pandas 0.24.2 numpy 1.17.3...
Unsupervised Closed-set Domain Adaptation (UDA) on the Office-Home dataset cd DINE time=`python ./get_time.py` gpu=0 for seed in 2020 2021 2022; do for src in 'Product' 'Real_World' 'Art' 'Clipart' ; do echo $src # training the source model first python DINE_dist.py --gpu_id...
Intelligent Vehicles}, year={2024}, volume={9}, number={2}, pages={3396-3408}, keywords={Semantics;Semantic segmentation;Training;Intelligent vehicles;Task analysis;SGML;Predictive models;Intelligent vehicles;semantic segmentation;domain adaptation;segment anything model}, doi={10.1109/TIV.2023.3344754}...