MixCompress: Mixture of Experts for Variable Rate Learned Image Compression
MixCompress introduces a unified framework for learned image compression that leverages sparse Mixture-of-Experts (MoE) and Mixture-of-Depths (MoD) architectures to support multiple bit-rates within a single model. By dynamically scaling model capacity and reducing feature entanglement, MixCompress matches or exceeds the performance of individually optimized single-rate models, setting a new Pareto frontier for efficient image coding.
Why it matters: This approach could significantly reduce storage and deployment costs by eliminating the need for multiple separate compression models, while improving efficiency in image compression tasks.
Full story at: arXiv Computer Vision ↗