IEEE

Boosting Universal Domain Adaptation in Remote Sensing With Dual-Classifiers Consistency Discrimination and Cross-Domain Feature Mixup

Abstract: In the field of remote sensing (RS) image classification, domain adaptation (DA) methods have been extensively utilized to overcome the challenges posed by data discrepancies between source ...
Scientific Research Publishing

A Lightweight Self-Supervised Representation Learning Framework for Depression Risk Profiling from Synthetic Daily Behavioural Trajectories ()

Detecting behavioural signatures of depression from everyday digital traces is a central challenge in computational psychiatry. Real-world datasets from smartphones and wearables often suffer from ...
Hacker

Machine Learning for the Birds: Building Your Own Bird Vocalization Classifier

Speech and language processing. At the end of the beginning. byPicture in the Noise@pictureinthenoise byPicture in the Noise@pictureinthenoise Speech and language processing. At the end of the ...
IEEE

Minimizing Adversarial Training Samples for Robust Image Classifiers: Analysis and Adversarial Example Generator Design

Abstract: Training deep neural networks (DNNs) with altered data, known as adversarial training, is essential for improving their robustness. A significant challenge emerges as the robustness ...