ROI-Packing: Efficient Region-Based Compression for Machine Vision
This addresses efficient compression for machine vision systems, offering significant gains without retraining, but it is incremental as it builds on existing compression methods.
The paper tackles the problem of image compression for machine vision by introducing ROI-Packing, which prioritizes regions of interest to achieve up to a 44.10% reduction in bitrate without accuracy loss and an 8.88% accuracy improvement at the same bitrate compared to VVC.
This paper introduces ROI-Packing, an efficient image compression method tailored specifically for machine vision. By prioritizing regions of interest (ROI) critical to end-task accuracy and packing them efficiently while discarding less relevant data, ROI-Packing achieves significant compression efficiency without requiring retraining or fine-tuning of end-task models. Comprehensive evaluations across five datasets and two popular tasks-object detection and instance segmentation-demonstrate up to a 44.10% reduction in bitrate without compromising end-task accuracy, along with an 8.88 % improvement in accuracy at the same bitrate compared to the state-of-the-art Versatile Video Coding (VVC) codec standardized by the Moving Picture Experts Group (MPEG).