Image compression with on-line and off-line learning

Images typically contain smooth regions, which are easily compressed by linear transforms, and high activity regions (edges, textures), which are harder to compress. To compress the first kind, we use a “zero” encoder that has infinite context, very low capacity, and which adapts very quickly to the content. For the second, we use an “interpolation” encoder, based on neural networks, which has high capacity, a finite-size context, and is trained off-line. The two encoders can be used separately or in combination. The zero-encoder surpasses JPEG2000 by 3.5% in overall compression, even though it is less efficient in high activity regions. Thanks to off-line training, the interpolation-encoder predicts high activity regions well, so it also matches the performance of JPEG2000, even though it does not use an arithmetic encoder and is less efficient in low activity regions. In both cases it is surprising that we match the stateof-the-art in image compression without using adaptive arithmetic encoding.