WITT: A Wireless Image Transmission Transformer for Semantic Communications

In this paper, we aim to redesign the vision Transformer (ViT) as a new backbone to realize semantic image transmission, termed wireless image transmission transformer (WITT). Previous works build upon convolutional neural networks (CNNs), which are inefficient in capturing global dependencies, resu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) S. 1 - 5
Hauptverfasser: Yang, Ke, Wang, Sixian, Dai, Jincheng, Tan, Kailin, Niu, Kai, Zhang, Ping
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 04.06.2023
Schlagworte:
Image communication
Image resolution
joint source and channel coding
Measurement
Modulation
Semantics
Speech coding
vision Transformer
Wireless communication
wireless image transmission
ISSN:2379-190X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we aim to redesign the vision Transformer (ViT) as a new backbone to realize semantic image transmission, termed wireless image transmission transformer (WITT). Previous works build upon convolutional neural networks (CNNs), which are inefficient in capturing global dependencies, resulting in degraded end-to-end transmission performance especially for high-resolution images. To tackle this, the proposed WITT employs Swin Transformers as a more capable backbone to extract long-range information. Different from ViTs in image classification tasks, WITT is highly optimized for image transmission while considering the effect of the wireless channel. Specifically, we propose a spatial modulation module to scale the latent representations according to channel state information, which enhances the ability of a single model to deal with various channel conditions. As a result, extensive experiments verify that our WITT attains better performance for different image resolutions, distortion metrics, and channel conditions. The code is available at https://github.com/KeYang8/WITT.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10094735