Compression for machines is an emerging field, where inputs are encoded while optimizing
the performance of down-stream automated analysis. In scalable coding for humans and …

We present methods for conditional and residual coding in the context of scalable coding for
humans and machines. Our focus is on optimizing the rate-distortion performance of the …

Over the last decade, deep learning has shown great success at performing computer vision
tasks, including classification, super-resolution, and style transfer. Now, we apply it to data …