We introduce deep learning based communication methods for successive
refinement of images over wireless channels. We present three different
strategies for progressive image transmission with deep JSCC, with different
complexity-performance trade-offs, all based on convolutional autoencoders.
Numerical results show that deep JSCC not only provides graceful degradation
with channel signal-to-noise ratio (SNR) and improved performance in low SNR
and low bandwidth regimes compared to state-of-the-art digital communication
techniques, but can also successfully learn a layered representation, achieving
performance close to a single-layer scheme. These results suggest that natural
images encoded with deep JSCC over Gaussian channels are almost successively
refinable.