Lossy image compression aims to represent images in as few bits as possible while maintaining fidelity to the original.
We empirically verify our approach on multiple domains involving compression of video and motion capture sequences, showing that our approaches can automatically achieve reductions in bit rates by learning how to discretize.
In this work, we attempt to bring these lines of research closer by revisiting vector quantization for image compression.
In particular, we derive a Hamilton-Jacobi-Bellman equation that governs the evolution of the log-densities of the underlying SDE marginals.
Current methods which compress multisets at an optimal rate have computational complexity that scales linearly with alphabet size, making them too slow to be practical in many real-world settings.
Most data is automatically collected and only ever "seen" by algorithms.
Ranked #1 on Image Compression on ImageNet (using extra training data)
Naively applied, our schemes would require more initial bits than the standard bits-back coder, but we show how to drastically reduce this additional cost with couplings in the latent space.
Finally, we demonstrate how the reconstruction algorithm can be extended with an amortized inference scheme on unknown attributes such as object pose.
This data set is the first publicly available set in OMR research with sufficient size to train and evaluate deep learning models.
The success of deep learning in numerous application domains created the de- sire to run and train them on mobile devices.