Multi-objective deep learning: Taxonomy and survey of the state of the art

S Peitz, SS Hotegni - arXiv preprint arXiv:2412.01566, 2024 - arxiv.org
Simultaneously considering multiple objectives in machine learning has been a popular
approach for several decades, with various benefits for multi-task learning, the consideration …

Unified detection of digital and physical face attacks

D Deb, X Liu, AK Jain - 2023 IEEE 17th International …, 2023 - ieeexplore.ieee.org
State-of-the-art defense mechanisms against face attacks achieve near perfect accuracies
within one of three attack categories, namely adversarial, digital manipulation, or physical …

Multi-task learning with attention: Constructing auxiliary tasks for learning to learn

B Li, A Dong - 2021 IEEE 33rd International Conference on …, 2021 - ieeexplore.ieee.org
With the development of deep learning in various fields, a deep learning method that can
optimize multiple target tasks at the same time, that is, deep multi-task learning (MTL), has …

Application of K-means clustering algorithm in evaluation and statistical analysis of internet financial transaction data

S Bo - arXiv preprint arXiv:2202.03146, 2022 - arxiv.org
The purpose is to promote the orderly development of China's Internet financial transactions
and minimize default and delinquency in Internet financial transactions. Based on the typical …