Progressive coding for autoencoders

Abstract

This disclosure provides methods, devices, and systems for image encoding. The present implementations more specifically relate to progressive encoding techniques for autoencoders. In some aspects, an image encoder may encode an image as a tensor of latent attributes having multiple channels based on one or more first layers of a neural network model, and recombine the tensor channels, in a prioritized order, based on one or more second layers of the neural network model. The image encoder may progressively transmit the recombined tensor channels over a communication channel based on the prioritized order. In some implementations, the image encoder may transmit the recombined tensor channels, in order of priority, so that channels assigned higher priorities are transmitted before channels assigned lower priorities.