FreqKD: Frequency-Decoupled Cross-Modal Knowledge Distillation for Infrared Object Detection
Researchers have developed FreqKD, a novel knowledge distillation framework designed to improve object detection in infrared imagery by leveraging large-scale RGB foundation models. The method addresses the challenge of modality differences by analyzing and decoupling spatial frequencies, applying distinct supervision strategies to low-frequency (structural) and high-frequency (textural) components. This approach enhances cross-modal consistency and leads to significant performance gains on various datasets and architectures, outperforming baseline methods. AI
IMPACT Enhances transfer learning for specialized imaging tasks, potentially improving autonomous systems and surveillance.