SR-DeepSC-Pro: Progressive Curriculum Learning with Adversarial Robustness for Satellite Semantic Communication

  • Do, Tung Son; 
  • Phung Truong, Thanh; 
  • Do, Quang Tuan; 
  • Cho, Sungrae
Citations

SCOPUS

0

초록

We present SR-DeepSC-Pro, an advanced super-resolution semantic communication system for bandwidth-constrained satellite image transmission. Through a novel two-stage training algorithm combining curriculum learning and adversarial robustness, our system achieves 10.2% higher PSNR (30.33 dB) while reducing satellite-side parameters by 26% and processing latency by 28.9%. SR-DeepSC-Pro maintains robust performance across SNR conditions with strongest gains at challenging low-SNR levels. This work demonstrates that advanced training strategies can overcome traditional quality-efficiency trade-offs, producing models that simultaneously excel in reconstruction performance and computational efficiency—critical advances for next-generation satellite communication systems.

키워드

6G; lightweight; semantic communication
제목
SR-DeepSC-Pro: Progressive Curriculum Learning with Adversarial Robustness for Satellite Semantic Communication
저자
Do, Tung Son; Phung Truong, Thanh; Do, Quang Tuan; Cho, Sungrae
DOI
10.23919/APCC64555.2025.11279743
발행일
2025
유형
Conference Paper
저널명
2025 30th Asia-Pacific Conference on Communications, APCC 2025