Device Interoperability for Learned Image Compression with Weights and Activations Quantization
This addresses the deployment challenge for learned image codecs by enabling error-free operation across different CPUs or GPUs, though it is incremental as it builds on existing state-of-the-art networks.
The paper tackled the device interoperability problem in learned image compression by introducing a quantization method for entropy networks, achieving cross-platform encoding and decoding with a minor performance deviation of 0.3% BD-rate from floating-point models.
Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance. In addition to good compression performance, device interoperability is essential for a compression codec to be deployed, i.e., encoding and decoding on different CPUs or GPUs should be error-free and with negligible performance reduction. In this paper, we present a method to solve the device interoperability problem of a state-of-the-art image compression network. We implement quantization to entropy networks which output entropy parameters. We suggest a simple method which can ensure cross-platform encoding and decoding, and can be implemented quickly with minor performance deviation, of 0.3% BD-rate, from floating point model results.