FSMODNet: A Closer Look at Few-Shot Detection in Multispectral Data
This work addresses the problem of detecting objects in visible and thermal imagery with minimal data, which is incremental as it builds on existing few-shot detection methods.
The paper tackles few-shot multispectral object detection by introducing FSMODNet, which uses cross-modality feature integration and deformable attention to improve detection with limited annotated data. Experimental results on two public datasets show it outperforms established baselines from state-of-the-art models.
Few-shot multispectral object detection (FSMOD) addresses the challenge of detecting objects across visible and thermal modalities with minimal annotated data. In this paper, we explore this complex task and introduce a framework named "FSMODNet" that leverages cross-modality feature integration to improve detection performance even with limited labels. By effectively combining the unique strengths of visible and thermal imagery using deformable attention, the proposed method demonstrates robust adaptability in complex illumination and environmental conditions. Experimental results on two public datasets show effective object detection performance in challenging low-data regimes, outperforming several baselines we established from state-of-the-art models. All code, models, and experimental data splits can be found at https://anonymous.4open.science/r/Test-B48D.