Prototype-Driven Adaptation for Few-Shot Object Detection
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot Object DetectionSimilar Papers 제목 키워드 기반
Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentation
Few-shot point cloud segmentation seeks to generate per-point masks for previously unseen categories, using only a minimal set of annotated point clouds as reference. Existing prototype-based methods rely on support prot…
Point Cloud SegmentationTransfer LearningBayPrAnoMeta: Bayesian Proto-MAML for Few-Shot Industrial Image Anomaly Detection
Industrial image anomaly detection is a challenging problem owing to extreme class imbalance and the scarcity of labeled defective samples, particularly in few-shot settings. We propose BayPrAnoMeta, a Bayesian generaliz…
Anomaly DetectionA Low-Shot Object Counting Network With Iterative Prototype Adaptation
We consider low-shot counting of arbitrary semantic categories in the image using only few annotated exemplars (few-shot) or no exemplars (no-shot). The standard few-shot pipeline follows extraction of appearance queries…
Exemplar-Free CountingObjectObject CountingObject LocalizationFSP-DETR: Few-Shot Prototypical Parasitic Ova Detection
Object detection in biomedical settings is fundamentally constrained by the scarcity of labeled data and the frequent emergence of novel or rare categories. We present FSP-DETR, a unified detection framework that enables…
Object DetectionExperience feedback using Representation Learning for Few-Shot Object Detection on Aerial Images
This paper proposes a few-shot method based on Faster R-CNN and representation learning for object detection in aerial images. The two classification branches of Faster R-CNN are replaced by prototypical networks for onl…
Few-Shot Object Detectionobject-detectionObject DetectionObject Detection In Aerial Images+1