Results 61 to 70 of about 3,036,262 (193)

Pseudo-class distribution guided multi-view unsupervised domain adaptation for hyperspectral image classification

International Journal of Applied Earth Observations and Geoinformation
Unsupervised domain adaptation (UDA) has made great progress in cross-scene hyperspectral image (HSI) classification. Existing methods focus on aligning the distribution of source domain (SD) and target domain (TD).
Jingpeng Gao, Xiangyu Ji, Geng Chen, Yuhang Huang, Fang Ye   +4 more
doaj   +1 more source

Unsupervised Adversarial Domain Adaptation with Error-Correcting Boundaries and Feature Adaption Metric for Remote-Sensing Scene Classification

Remote Sensing, 2021
Unsupervised domain adaptation (UDA) based on adversarial learning for remote-sensing scene classification has become a research hotspot because of the need to alleviating the lack of annotated training data.
Chenhui Ma, Dexuan Sha, Xiaodong Mu
doaj   +1 more source

AI‐Based D‐Amino Acid Substitution for Optimizing Antimicrobial Peptides to Treat Multidrug‐Resistant Bacterial Infection

Advanced Science, Volume 13, Issue 10, 18 February 2026.
This study constructed the first D‐amino acid antimicrobial peptide dataset and developed an AI model for efficient screening of substitution sites, with 80% of candidate peptides showing enhanced activity. The lead peptide dR2‐1 demonstrated potent antimicrobial activity in vitro and in vivo, high stability, and low toxicity.
Yinuo Zhao, Qingzhou Kong, Haifan Gong, Lixiang Li, Jialu Fu, Boyao Wan, Peizhu Wang, Xiaojuan Li, Yue Wang, Jinghui Zhang, Yanbo Yu, Xiaoyun Yang, Xiuli Zuo, Haina Wang, Yanqing Li   +14 more
wiley   +1 more source

Unsupervised Intralingual and Cross-Lingual Speaker Adaptation for HMM-Based Speech Synthesis Using Two-Pass Decision Tree Construction [PDF]

, 2010
Hidden Markov model (HMM)-based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset ...
Matthew Gibson, William Byrne
core   +2 more sources

Informative Feature Disentanglement for Unsupervised Domain Adaptation [PDF]

, 2021
Unsupervised Domain Adaptation (UDA) aims at learning a classifier for an unlabeled target domain by transferring knowledge from a labeled source domain with a related but different distribution. The strategy of aligning the two domains in latent feature
Guo, Deke, Liu, Li, Liao, Qing, Kuang, Gangyao, Zhao, Lingjun, Deng, Wanxia, Pietikäinen, Matti, Hu, Dewen   +7 more
core   +1 more source

Lightweight and Robust Cross-Domain Microseismic Signal Classification Framework with Bi-Classifier Adversarial Learning

Engineering
Automatic identification of microseismic (MS) signals is crucial for early disaster warning in deep underground engineering. However, three major challenges remain for practical deployment, namely limited resources, severe noise interference, and data ...
Dingran Song, Feng Dai, Yi Liu, Hao Tan, Mingdong Wei   +4 more
doaj   +1 more source

A Fine-Grained Unsupervised Domain Adaptation Framework for Semantic Segmentation of Remote Sensing Images

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023
Unsupervised domain adaptation (UDA) aims at adapting a model from the source domain to the target domain by tackling the issue of domain shift.
Luhan Wang, Pengfeng Xiao, Xueliang Zhang, Xinyang Chen   +3 more
doaj   +1 more source

Synthetic‐to‐Real Few‐Shot Crowd Counting via Scene Adaptive Meta Learning

IET Computer Vision, Volume 20, Issue 1, January/December 2026.
This paper introduces the novel task of synthetic‐to‐real few‐shot crowd counting (S2R‐FSCC), which leverages large‐scale synthetic data for training while requiring only minimal annotated real‐world images for adaptation. To address the significant domain shift, the authors propose a scene adaptive meta‐learner (SAML) embedded in a meta‐learning ...
Xiang Lin, Longxi Zheng, Jingze Su, Xiaoyu Liao, Luojun Lin, Xingsi Xue, Wenxi Liu   +6 more
wiley   +1 more source

Dual-Consistency Input-Space Domain Adaptation for Remote Sensing Image Semantic Segmentation via SSC-CycleGAN

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
In remote sensing image semantic segmentation, unsupervised domain adaptation (UDA) addresses two key challenges: scarce labeled data and poor cross-domain generalization. By narrowing domain shift between labeled source and unlabeled target domains, UDA
Longbao Wang, Yiding Ma, Meng Ding, Yinqi Luan, Shun Luo, Xiaoyang Meng, Yueyang Mao, Hongmin Gao   +7 more
doaj   +1 more source

MSAA‐MSDA: A Multi‐Source Domain Adaptation Method for Remote Sensing Scene Classification Based on Multi‐Scale Attention Aggregation

IET Image Processing, Volume 20, Issue 1, January/December 2026.
ABSTRACT Remote sensing scene classification is often challenged by domain shifts arising from variations in regions and sensor types, which can significantly degrade performance when models are applied to unlabelled target domains. Multi‐source domain adaptation (MSDA) leverages multiple labelled source domains to improve generalization, but its ...
Wei Dai, Haixia Xu, Liming Yuan, Xinyu Wang, Xianbin Wen   +4 more
wiley   +1 more source