Score: 1

Multi-hop Deep Joint Source-Channel Coding with Deep Hash Distillation for Semantically Aligned Image Retrieval

Published: October 8, 2025 | arXiv ID: 2510.06868v1

By: Didrik Bergström, Deniz Gündüz, Onur Günlü

Potential Business Impact:

Makes pictures sent over the internet clearer.

Business Areas:
Darknet Internet Services

We consider image transmission via deep joint source-channel coding (DeepJSCC) over multi-hop additive white Gaussian noise (AWGN) channels by training a DeepJSCC encoder-decoder pair with a pre-trained deep hash distillation (DHD) module to semantically cluster images, facilitating security-oriented applications through enhanced semantic consistency and improving the perceptual reconstruction quality. We train the DeepJSCC module to both reduce mean square error (MSE) and minimize cosine distance between DHD hashes of source and reconstructed images. Significantly improved perceptual quality as a result of semantic alignment is illustrated for different multi-hop settings, for which classical DeepJSCC may suffer from noise accumulation, measured by the learned perceptual image patch similarity (LPIPS) metric.

Page Count
5 pages

Category
Computer Science:
Information Theory