DeepJSCC-l++: Robust and Bandwidth-Adaptive Wireless Image Transmission
Chenghong Bian, Yulin Shao, Deniz Gunduz

TL;DR
DeepJSCC-l++ is a transformer-based wireless image transmission scheme that adaptively handles multiple bandwidth ratios and SNRs with a single model, outperforming traditional digital methods.
Contribution
The paper introduces DeepJSCC-l++, a novel ViT-based model that adaptively manages various bandwidths and SNRs using a new training methodology with side information.
Findings
Achieves adaptive performance across multiple bandwidth ratios and SNRs.
Outperforms digital BPG + channel coding baseline in simulations.
Uses shifted window transformer as backbone for improved robustness.
Abstract
This paper presents a novel vision transformer (ViT) based deep joint source channel coding (DeepJSCC) scheme, dubbed DeepJSCC-l++, which can be adaptive to multiple target bandwidth ratios as well as different channel signal-to-noise ratios (SNRs) using a single model. To achieve this, we train the proposed DeepJSCC-l++ model with different bandwidth ratios and SNRs, which are fed to the model as side information. The reconstruction losses corresponding to different bandwidth ratios are calculated, and a new training methodology is proposed, which dynamically assigns different weights to the losses of different bandwidth ratios according to their individual reconstruction qualities. Shifted window (Swin) transformer, is adopted as the backbone for our DeepJSCC-l++ model. Through extensive simulations it is shown that the proposed DeepJSCC-l++ and successive refinement models can adapt…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Data Compression Techniques · Video Coding and Compression Technologies · Sparse and Compressive Sensing Techniques
MethodsAttention Is All You Need · Residual Connection · Softmax · Layer Normalization · Linear Layer · Multi-Head Attention · Dense Connections · Vision Transformer
