Leveraging Overfitting for Low-Complexity and Modality-Agnostic Joint Source-Channel Coding

TL;DR

Implicit-JSCC is a novel overfitted joint source-channel coding method that offers a storage-free, low-complexity, modality-agnostic solution for efficient image transmission, achieving state-of-the-art results in high SNR regimes.

Contribution

It introduces Implicit-JSCC, a one-shot, overfitted coding paradigm that eliminates the need for training datasets and pre-trained models, enabling efficient, low-complexity, modality-agnostic image transmission.

Findings

Achieves 1000x lower decoding complexity compared to traditional methods.

Requires as few as 607 model parameters and 641 multiplications per pixel.

Outperforms existing methods in high SNR regimes.

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.