Results 81 to 90 of about 2,905 (180)
Discriminator-free adversarial domain adaptation with information balance
Electronic Research ArchiveIn the realm of Unsupervised Domain Adaptation (UDA), adversarial learning has achieved significant progress. Existing adversarial UDA methods typically employ additional discriminators and feature extractors to engage in a max-min game.
Hui Jiang +4 more
doaj +1 more source
IET Image Processing, Volume 18, Issue 14, Page 4680-4694, 11 December 2024.We design an adaptive foreground enhancement module (AFEM), which can adaptively enhance the foreground pedestrian features of the input features, obtain more discriminative features, enhance the clustering effect and more accurate pseudo labels. We propose an adaptive information supplement (AIS) method that can adaptively supplement global features ...
Qiang Wang +4 more
wiley +1 more source
Adversarial Learning and Interpolation Consistency for Unsupervised Domain Adaptation
IEEE Access, 2019 Unsupervised domain adaptation (UDA) aims to learn a prediction model for the target domain given labeled source data and unlabeled target data. Impressive progress has been made by adversarial learning-based methods that align distributions across ...
Xin Zhao, Shengsheng Wang
doaj +1 more source
Geomatics, Natural Hazards & RiskIn forest fire smoke detection tasks, variations in data distribution caused by deployment environments, acquisition devices, and smoke characteristics, along with the scarcity of fire incidents, make it difficult for models to generalize across all ...
Peixian Jin +5 more
doaj +1 more source
EM-UDA: Emotion Detection Using Unsupervised Domain Adaptation for Classification of Facial Images
IEEE AccessFacial 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. Most methods proposed for facial emotion recognition use supervised learning.
Priti R. Jain +2 more
openaire +2 more sources
Convolutional Neural Networks for Road Detection: An Unsupervised Domain Adaptation Approach [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesDue 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
Proceedings of the AAAI Conference on Artificial IntelligenceCryo-Electron Tomography (cryo-ET) is a 3D imaging technology that facilitates the study of macromolecular structures at near-atomic resolution. Recent volumetric segmentation approaches on cryo-ET images have drawn widespread interest in the biological sector.
Li, Haoran +8 more
openaire +2 more sources
IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingIn remote sensing image classification task, it is often apply a model trained on one dataset (source domain) to another dataset (target domain). However, due to the presence of domain shift between these domains where data are not independent and ...
Junsong Leng +5 more
doaj +1 more source
International Journal of Applied Earth Observations and GeoinformationDomain adaptation is crucial for information integration of remote sensing systems, such as satellite constellations and space stations, to intelligently achieving full domain awareness. The conventional methods focus on aligning spatial features without
Binquan Li +4 more
doaj +1 more source