Results 81 to 90 of about 3,613,102 (160)

Convolutional Neural Networks for Road Detection: An Unsupervised Domain Adaptation Approach [PDF]

open access: yesThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Due to the frequent road network changes, keeping them updated is fundamental for several purposes. Currently, models based on Deep Learning (DL), specifically, Convolutional Neural Networks (CNNs), such as encoder-decoder type, are state-of-the-art for ...
G. R. Collegio   +3 more
doaj   +1 more source

UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework [PDF]

open access: yes
In this work, we take a deeper look into the diverse factors that influence the efficacy of modern unsupervised domain adaptation (UDA) methods using a large-scale, controlled empirical study.
Ravichandran, Sreyas   +2 more
core  

Domain Confused Contrastive Learning for Unsupervised Domain Adaptation [PDF]

open access: yes, 2022
In this work, we study Unsupervised Domain Adaptation (UDA) in a challenging self-supervised approach. One of the difficulties is how to learn task discrimination in the absence of target labels.
Pan, Sinno Jialin   +3 more
core  

Toward Pose Invariant Bionic Limb Control: A Comparative Study of Two Unsupervised Domain Adaptation Methods

open access: yesIEEE Access
Bionic limb control through myoelectric pattern recognition, offering intuitive decoding of motor intent, can improve the quality of life for individuals with amputations.
Alexander Hannius   +2 more
doaj   +1 more source

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

open access: yesIEEE 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   +7 more
doaj   +1 more source

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

open access: yesEngineering
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   +4 more
doaj   +1 more source

EM-UDA: Emotion Detection Using Unsupervised Domain Adaptation for Classification of Facial Images

open access: yesIEEE Access
Facial expressions can be used to interpret human feelings. They can be successfully used to assess the mood of a person. Accurate prediction of moods can prove to be of immense help in several areas including the mental health of an individual.
Priti R. Jain   +2 more
doaj   +1 more source

Robust unsupervised domain adaptation for medical image segmentation via frequency-conditioned graph diffusion

open access: yesScientific Reports
Cross-domain variability in medical imaging, arising from differences in scanners, acquisition protocols, and patient populations, remains a major challenge for reliable semantic segmentation.
Usman Ahmad Usmani   +2 more
doaj   +1 more source

Source-free domain adaptation for semantic image segmentation using internal representations

open access: yesFrontiers in Big Data
Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance.
Serban Stan, Mohammad Rostami
doaj   +1 more source

HDRSeg-UDA: Semantic Segmentation for HDR Images with Unsupervised Domain Adaptation

open access: yesSmart Cities
Accurate detection and localization of traffic objects are essential for autonomous driving tasks such as path planning. While semantic segmentation is able to provide pixel-level classification, existing networks often fail under challenging conditions ...
Huei-Yung Lin, Ming-Yiao Chen
doaj   +1 more source

Home - About - Disclaimer - Privacy