Results 51 to 60 of about 3,020,093 (290)

Unsupervised Domain Adaptation with Similarity Learning [PDF]

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018
The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to domain adaptation consist of two steps: (i) learn features that preserve a low risk on labeled samples (source domain)
openaire   +3 more sources

Unsupervised adaptation of PLDA models for broadcast diarization

EURASIP Journal on Audio, Speech, and Music Processing, 2019
We present a novel model adaptation approach to deal with data variability for speaker diarization in a broadcast environment. Expensive human annotated data can be used to mitigate the domain mismatch by means of supervised model adaptation approaches ...
Ignacio Viñals, Alfonso Ortega, Jesús Villalba, Antonio Miguel, Eduardo Lleida   +4 more
doaj   +1 more source

Dual adversarial models with cross-coordination consistency constraint for domain adaption in brain tumor segmentation

Frontiers in Neuroscience, 2023
The brain tumor segmentation task with different domains remains a major challenge because tumors of different grades and severities may show different distributions, limiting the ability of a single segmentation model to label such tumors.
Chuanbo Qin, Wanying Li, Bin Zheng, Junying Zeng, Shufen Liang, Xiuping Zhang, Wenguang Zhang   +6 more
doaj   +1 more source

Unsupervised Domain Adaptation by Mapped Correlation Alignment

IEEE Access, 2018
The goal of unsupervised domain adaptation aims to utilize labeled data from source domain to annotate the target-domain data, which has none of the labels.
Yun Zhang, Nianbin Wang, Shaobin Cai, Lei Song   +3 more
doaj   +1 more source

EQAdap: Equipollent Domain Adaptation Approach to Image Deblurring

IEEE Access, 2022
In this paper, we present an end-to-end unsupervised domain adaptation approach to image deblurring. This work focuses on learning and generalizing the complex latent space of the source domain and transferring the extracted information to the unlabeled ...
Ibsa Jalata, Naga Venkata Sai Raviteja Chappa, Thanh-Dat Truong, Pierce Helton, Chase Rainwater, Khoa Luu   +5 more
doaj   +1 more source

UAV-based Unsupervised Domain Adaptation for Road Extraction [PDF]

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Despite advances in Deep Learning (DL) for road extraction, this task remains challenging. First, domain shifts in data distribution hinder the inference of pre-trained models to new areas, leading to a drop in classification accuracy.
G. R. Collegio, A. G. Guimarães Filho, A. P. Dal Poz, A. Habib   +3 more
doaj   +1 more source

Digital Cognitive Phenotyping for Differential Diagnosis and Monitoring in Neurological Conditions

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective To assess the utility, accessibility, and equivalence to supervised scales of online cognitive assessment in older individuals with cognitive impairment. Methods Patients with Alzheimer's disease (AD, n = 31), idiopathic normal pressure hydrocephalus (iNPH, n = 26), and traumatic brain injury (TBI, n = 23) completed online cognitive ...
Martina Del Giovane, Valentina Giunchiglia, Michael C. B. David, Magdalena A. Kolanko, William R. Trender, Peter J. Hellyer, Harmeena Kaur, David J. Sharp, Christopher Carswell, Paresh A. Malhotra, Adam Hampshire   +10 more
wiley   +1 more source

Source Free Unsupervised Graph Domain Adaptation [PDF]

, 2023
Graph Neural Networks (GNNs) have achieved great success on a variety of tasks with graph-structural data, among which node classification is an essential one. Unsupervised Graph Domain Adaptation (UGDA) shows its practical value of reducing the labeling
Zhang, Dongmei, Zheng, Yujia, Li, Zelin, Han, Shi, Du, Lun, Mao, Haitao, Fu, Qiang, Chen, Xu   +7 more
core   +1 more source

Unsupervised Domain Adaptation for Visual Navigation

CoRR, 2020
Advances in visual navigation methods have led to intelligent embodied navigation agents capable of learning meaningful representations from raw RGB images and perform a wide variety of tasks involving structural and semantic reasoning. However, most learning-based navigation policies are trained and tested in simulation environments.
Shangda Li, Devendra Singh Chaplot, Yao-Hung Hubert Tsai, Yue Wu 0001, Louis-Philippe Morency, Ruslan Salakhutdinov   +5 more
openaire   +3 more sources

Integrated PANoptosis Profiling Identifies Immunosuppressive Subtypes and a Prognostic Signature With Functional Validation of MLKL in Glioblastoma

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective The prognosis of glioblastoma (GBM) remains highly unfavorable, largely due to high tumor heterogeneity and an immunosuppressive microenvironment. However, the functional role of PANoptosis in this context is poorly understood. Methods Patients were stratified via K‐means clustering. A risk score model was constructed using prognosis‐
Langfei Tian, Minghui Zhao, Yuanbo Hu, Kaiyue Wang, Haiguang Liu, Zetong Bai, Kebin Zheng   +6 more
wiley   +1 more source