Improving the Generalization Ability of NN Equalizers of VLCs Using Channel Representation
Sign Up to like & getrecommendations! Published in 2025 at "Journal of Lightwave Technology"
DOI: 10.1109/jlt.2024.3519782
Abstract: This research focuses on enhancing the generalization capabilities of neural network (NN)-based equalizers within visible light communication (VLC) systems. NN equalizers often suffer from performance degradation when exposed to varying system operational conditions and external… read more here.
Keywords: improving generalization; generalization ability; representation; channel representation ... See more keywords
Improving Generalization of Deepfake Detectors by Imposing Gradient Regularization
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2024.3396064
Abstract: The rapid development of face forgery technology has posed a significant threat to information security. While deepfake detection has proven to be an effective countermeasure, it often struggles to detect fake images generated by unknown… read more here.
Keywords: gradient regularization; deepfake detectors; improving generalization; regularization ... See more keywords
Sharpness-Aware Lookahead for Accelerating Convergence and Improving Generalization
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2024.3444002
Abstract: Lookahead is a popular stochastic optimizer that can accelerate the training process of deep neural networks. However, the solutions found by Lookahead often generalize worse than those found by its base optimizers, such as SGD… read more here.
Keywords: improving generalization; aware lookahead; sharpness aware; optimizer ... See more keywords