Leveraging Overfitting for Low-Complexity and Modality-Agnostic Joint Source-Channel Coding
Authors:
Preprint
Abstract
This paper introduces Implicit-JSCC, a novel overfitted joint source-channel coding paradigm that directly optimizes channel symbols and a lightweight neural decoder for each source. This instance-specific strategy eliminates the need for training datasets or pre-trained models, enabling a storage-free, modality-agnostic solution. As a low-complexity alternative, Implicit-JSCC achieves efficient image transmission with around 1000x lower decoding complexity, using as few as 607 model parameters and 641 multiplications per pixel. This overfitted design inherently addresses source generalizability and achieves state-of-the-art results in the high SNR regimes, underscoring its promise for future communication systems, especially streaming scenarios where one-time offline encoding supports multiple online decoding.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Semantic Prior Aided Channel-Adaptive Equalizing and De-Noising Semantic Communication System With Latent Diffusion ModelIEEE Transactions on Wireless Communications, 2025
- Process-and-Forward: Deep Joint Source-Channel Coding Over Cooperative Relay NetworksIEEE Journal on Selected Areas in Communications, 2025
- Deep Joint Source-Channel Coding for Adaptive Image Transmission Over MIMO ChannelsIEEE Transactions on Wireless Communications, 2024
- SwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel CodingIEEE Transactions on Cognitive Communications and Networking, 2024
- Transformer-Aided Wireless Image Transmission With Channel FeedbackIEEE Transactions on Wireless Communications, 2024
- DeepWiVe: Deep-Learning-Aided Wireless Video TransmissionIEEE Journal on Selected Areas in Communications, 2022
- Nonlinear Transform Source-Channel Coding for Semantic CommunicationsIEEE Journal on Selected Areas in Communications, 2022
- Deep Joint Source-Channel Coding for Wireless Image TransmissionIEEE Transactions on Cognitive Communications and Networking, 2019