MambaJSCC: Adaptive Deep Joint Source-Channel Coding with Generalized State Space Model

TL;DR

MambaJSCC introduces an adaptive deep joint source-channel coding architecture utilizing generalized state space models and channel adaptation techniques, achieving superior performance with lower computational costs for wireless image transmission.

Contribution

The paper presents a novel JSCC architecture with GSSM and CSI-ReST, enabling effective channel adaptation without extra overhead, and proves its theoretical capacity to capture global information.

Findings

Outperforms existing JSCC methods like SwinJSCC.

Reduces parameter size and computational overhead.

Enhances inference speed and robustness.

Abstract

Lightweight and efficient neural network models for deep joint source-channel coding (JSCC) are crucial for semantic communications. In this paper, we propose a novel JSCC architecture, named MambaJSCC, that achieves state-of-the-art performance with low computational and parameter overhead. MambaJSCC utilizes the visual state space model with channel adaptation (VSSM-CA) blocks as its backbone for transmitting images over wireless channels, where the VSSM-CA primarily consists of the generalized state space models (GSSM) and the zero-parameter, zero-computational channel adaptation method (CSI-ReST). We design the GSSM module, leveraging reversible matrix transformations to express generalized scan expanding operations, and theoretically prove that two GSSM modules can effectively capture global information. We discover that GSSM inherently possesses the ability to adapt to channels, a form of endogenous intelligence. Based on this, we design the CSI-ReST method, which injects channel state information (CSI) into the initial state of GSSM to utilize its native response, and into the residual state to mitigate CSI forgetting, enabling effective channel adaptation without introducing additional computational and parameter overhead. Experimental results show that MambaJSCC not only outperforms existing JSCC methods (e.g., SwinJSCC) across various scenarios but also significantly reduces parameter size, computational overhead, and inference delay.