Prototype-Driven Adaptation for Few-Shot Object Detection
This work addresses few-shot object detection for computer vision applications, presenting an incremental improvement over existing methods.
The paper tackles the problem of base-class bias and unstable calibration in few-shot object detection by proposing Prototype-Driven Alignment (PDA), a lightweight plug-in metric head for DeFRCN, which improves novel-class performance with minimal impact on base classes and negligible computational overhead, as shown in experiments on VOC FSOD and GFSOD benchmarks.
Few-shot object detection (FSOD) often suffers from base-class bias and unstable calibration when only a few novel samples are available. We propose Prototype-Driven Alignment (PDA), a lightweight, plug-in metric head for DeFRCN that provides a prototype-based "second opinion" complementary to the linear classifier. PDA maintains support-only prototypes in a learnable identity-initialized projection space and optionally applies prototype-conditioned RoI alignment to reduce geometric mismatch. During fine-tuning, prototypes can be adapted via exponential moving average(EMA) updates on labeled foreground RoIs-without introducing class-specific parameters-and are frozen at inference to ensure strict protocol compliance. PDA employs a best-of-K matching scheme to capture intra-class multi-modality and temperature-scaled fusion to combine metric similarities with detector logits. Experiments on VOC FSOD and GFSOD benchmarks show that PDA consistently improves novel-class performance with minimal impact on base classes and negligible computational overhead.