XAI based Performance Preserving Adaptive Image Compression for Efficient Satellite Communication
This addresses the need for efficient satellite communication by reducing data transmission overhead while preserving analysis performance, though it appears incremental as it builds on existing compression and XAI methods.
The authors tackled the problem of high transmission overhead in satellite image analysis by proposing RDIC, a reasoning-based image compression scheme that uses pixel importance scores from the analysis model, achieving high compression rates with low accuracy loss.
In the era of multinational cooperation, gathering and analyzing the satellite images are getting easier and more important. Typical procedure of the satellite image analysis include transmission of the bulky image data from satellite to the ground producing significant overhead. To reduce the amount of the transmission overhead while making no harm to the analysis result, we propose a novel image compression scheme RDIC in this paper. RDIC is a reasoning based image compression scheme that compresses an image according to the pixel importance score acquired from the analysis model itself. From the experimental results we showed that our RDIC scheme successfully captures the important regions in an image showing high compression rate and low accuracy loss.