DenoMAE: A Multimodal Autoencoder for Denoising Modulation Signals

We propose Denoising Masked Autoencoder (DenoMAE), a novel multimodal autoencoder framework for denoising modulation signals during pretraining. DenoMAE extends the concept of masked autoencoders by incorporating multiple input modalities, including noise as an explicit modality, to enhance cross-mo...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE communications letters Ročník 29; číslo 7; s. 1659 - 1663
Hlavní autori: Faysal, Atik, Boushine, Taha, Rostami, Mohammad, Roshan, Reihaneh Gh, Wang, Huaxia, Muralidhar, Nikhil, Sahoo, Avimanyu, Yao, Yu-Dong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.07.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Adaptation models
Autoencoders
Classification
Constellation diagram
constellation diagrams
Decoding
denoising
Image reconstruction
Learning
Modulation
modulation classification
Multi-modality
Noise reduction
Signal to noise ratio
Training
Transformers
vision transformer
ISSN:1089-7798, 1558-2558
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:We propose Denoising Masked Autoencoder (DenoMAE), a novel multimodal autoencoder framework for denoising modulation signals during pretraining. DenoMAE extends the concept of masked autoencoders by incorporating multiple input modalities, including noise as an explicit modality, to enhance cross-modal learning and improve denoising performance. The network is pre-trained using unlabeled noisy modulation signals and constellation diagrams, effectively learning to reconstruct their equivalent noiseless signals and diagrams. DenoMAE achieves state-of-the-art accuracy in automatic modulation classification (AMC) tasks with significantly fewer training samples, demonstrating a <inline-formula> <tex-math notation="LaTeX">10\times </tex-math></inline-formula> reduction in unlabeled pretraining data and a <inline-formula> <tex-math notation="LaTeX">3\times </tex-math></inline-formula> reduction in labeled fine-tuning data compared to existing approaches. Moreover, our model exhibits robust performance across varying Signal-to-Noise Ratios (SNRs) and supports extrapolation on unseen lower SNRs. The results indicate that DenoMAE is an efficient, flexible, and data-efficient solution for denoising and classifying modulation signals in challenging, noise-intensive environments. Our codes are public at https://github.com/atik666/denoMae/tree/master .
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1089-7798
1558-2558
DOI:10.1109/LCOMM.2025.3570602