A Unified Image Compression Method for Human Perception and Multiple Vision Tasks

Recent advancements in end-to-end image compression demonstrate the potential to surpass traditional codecs regarding rate-distortion performance. However, current methods either prioritize human perceptual quality or solely optimize for one or a few predetermined downstream tasks, neglecting a more common scenario that involves a variety of unforeseen machine vision tasks. In this paper, we propose a Diffusion-based Multiple-Task Unified Image Compression framework that aims to expand the boundary of traditional image compression by incorporating human perception and multiple vision tasks in open-set scenarios. Our proposed method comprises a Multi-Task Collaborative Embedding module and a Diffusion-based Invariant Knowledge Learning module. The former module facilitates collaborative embedding for multiple tasks, while the latter module boosts generalization toward unforeseen tasks by distilling the invariant knowledge from seen vision tasks. Experiments show that the proposed method extracts compact and versatile embeddings for human and machine vision collaborative compression, resulting in superior performance. Specifically, our method outperforms the state-of-the-art by 52.25%/51.68%/48.87%/48.07%/6.29% BD-rate reduction in terms of mAP/mAP/aAcc/PQ-all/accuracy on the MS-COCO for object detection/instance segmentation/semantic segmentation/panoptic segmentation and video question answering tasks, respectively.