Multi-hop Deep Joint Source-Channel Coding with Deep Hash Distillation for Semantically Aligned Image Retrieval
By: Didrik Bergström, Deniz Gündüz, Onur Günlü
Potential Business Impact:
Makes pictures sent over the internet clearer.
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.
Similar Papers
Semantic Channel Equalization Strategies for Deep Joint Source-Channel Coding
Machine Learning (CS)
Fixes AI messages sent between different devices.
DeepStream: Prototyping Deep Joint Source-Channel Coding for Real-Time Multimedia Transmissions
Signal Processing
Sends pictures and videos better with less signal.
Distributed Image Semantic Communication via Nonlinear Transform Coding
Information Theory
Lets computers share pictures better over the internet.