AD-SRF: Attack-Defense Semantic Reinforcement for Multi-Modal Image Fusion
To address this challenge, we propose an attack-defense semantic reinforcement framework for multi-modal image fusion, termed AD-SRF.
ProofPaper ↗
Key points
- Existing image fusion methods struggle to balance visual quality and semantic attributes due to the inherent conflict between their optimization objectives.
- First, we develop a transformer-based restorative visual fusion network as a strong visual baseline.
- Second, we introduce an attack-defense game mechanism to strengthen the semantic attributes of the fused images.
- Through iterative adversarial interaction, this mechanism drives the defender to continually strengthen the fused image's semantic attributes, boosting downstream segmentation performance without compromising visual quality.
Sources (1)
- [1]AD-SRF: Attack-Defense Semantic Reinforcement for Multi-Modal Image FusionarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 02:38 AM
To address this challenge, we propose an attack-defense semantic reinforcement framework for multi-modal image fusion, termed AD-SRF.
Existing image fusion methods struggle to balance visual quality and semantic attributes due to the inherent conflict between their optimization objectives.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 9, 2026Win-Win Fusion: Multi-Modal Image Fusion with Visual-Semantic Collaboration
- Oct 9, 2026Structure-Aware Matching for Robust UAV Thermal-to-Satellite Geo-Localization
- Oct 8, 2026Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
- Oct 8, 2026LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
- Oct 7, 2026[AINews] Claude Haiku 5.5 — better than GPT-6 Luna at the same pricing