WITT: A Wireless Image Transmission Transformer for Semantic Communications

Author name not available (Why is that?)

Publication date: 2 November 2022

Abstract: 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.

Has companion code repository: https://github.com/keyang8/witt

This page was built for publication: WITT: A Wireless Image Transmission Transformer for Semantic Communications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6415888)