Faster and Better: Reinforced Collaborative Distillation and Self-Learning for Infrared-Visible Image Fusion
This addresses the problem of efficient multi-modal image fusion for applications like scene perception, though it appears to be an incremental improvement over existing distillation approaches.
The paper tackles the challenge of achieving high-quality infrared-visible image fusion with lightweight models by proposing a reinforcement learning-driven collaborative distillation and self-learning framework. The method significantly improves student model performance and achieves better fusion results compared to existing techniques.
Infrared and visible image fusion plays a critical role in enhancing scene perception by combining complementary information from different modalities. Despite recent advances, achieving high-quality image fusion with lightweight models remains a significant challenge. To bridge this gap, we propose a novel collaborative distillation and self-learning framework for image fusion driven by reinforcement learning. Unlike conventional distillation, this approach not only enables the student model to absorb image fusion knowledge from the teacher model, but more importantly, allows the student to perform self-learning on more challenging samples to enhance its capabilities. Particularly, in our framework, a reinforcement learning agent explores and identifies a more suitable training strategy for the student. The agent takes both the student's performance and the teacher-student gap as inputs, which leads to the generation of challenging samples to facilitate the student's self-learning. Simultaneously, it dynamically adjusts the teacher's guidance strength based on the student's state to optimize the knowledge transfer. Experimental results demonstrate that our method can significantly improve student performance and achieve better fusion results compared to existing techniques.