UAV imagery is particularly difficult for object detection because targets occupy few pixels, occur in dense or occluded groups, and must be separated from extensive background texture. Adding a high-resolution detection layer improves the visibility of tiny instances, but it also carries road markings, building contou...
A Difference-Gated Interaction and Change-Aware Cross-Temporal Fusion Network (DCAFNet) within a unified coarse-to-fine framework is proposed, demonstrating that DCAFNet consistently outperforms ten state-of-the-art methods.
Le-Le Li, Pan-Pan Zheng, Lie-Jun Wang et al.· Remote Sensing· 0 citations
Experiments show that InfRA-FL outperforms state-of-the-art baselines by 5–10% in accuracy while accelerating convergence, establishing that principled information-theoretic observation and robust reward design suffice to secure RL-driven federated learning against targeted poisoning.