Robust Nonlinear Transform Coding: A Framework for Generalizable Joint Source-Channel Coding

TL;DR

Robust-NTC is integrated into an orthogonal frequency-division multiplexing system, where a unified resource allocation framework jointly optimizes latent quantization, bit allocation, modulation order, and power allocation to minimize transmission latency while guaranteeing learned distortion targets.

Abstract

This paper proposes robust nonlinear transform coding (Robust-NTC), a generalizable digital joint source-channel coding (JSCC) framework that couples variational latent modeling with channel adaptive transmission. Unlike learning-based JSCC methods that implicitly absorb channel variations, Robust-NTC explicitly models element-wise latent distributions via a variational objective with a Gaussian proxy for quantization and channel noise, allowing encoder-decoder to capture latent uncertainty without channel-specific training. Using the learned statistics, Robust-NTC also facilitates rate-distortion optimization to adaptively select element-wise quantizers and bit depths according to online channel condition. To support practical deployment, Robust-NTC is integrated into an orthogonal frequency-division multiplexing (OFDM) system, where a unified resource allocation framework jointly optimizes latent quantization, bit allocation, modulation order, and power allocation to minimize transmission latency while guaranteeing learned distortion targets. Simulation results demonstrate that for practical OFDM systems, Robust-NTC achieves superior rate-distortion efficiency and stable reconstruction fidelity compared to digital JSCC baselines across wide-ranging SNR conditions.

Figures (8)

• Figure 1: MSE performance of quantizer designs across different bit depths for various optimized-test flip probability pairs $(\epsilon_{\rm opt},\epsilon_{\rm test})$.
• Figure 2: System architecture of the proposed Robust-NTC: (a) overall system model and (b) proxy model for tractable optimization.
• Figure 3: OFDM transmission model with the associated optimization framework.
• Figure 4: Empirical CDFs of normalized latents $(y_i-\mu_i)/\sigma_i$ obtained from the CIFAR-10 test dataset using the model learned under the proposed Robust-NTC framework, compared with the standard Gaussian reference $\mathcal{N}(0,1)$.
• Figure 5: Comparison of the proposed Robust-NTC and baseline schemes in terms of PSNR versus the number of OFDM symbols under different SNR levels, evaluated on the CIFAR-10 dataset.