Prototype-Conditioned Generative Adversarial Network for Few-Shot Remote Sensing Object Detection

Abstract

Few-shot object detection (FSOD) in remote sensing imagery faces critical challenges stemming from extreme data scarcity, specifically inadequate feature coverage, severe class imbalance, and pervasive incomplete annotations. To address these interconnected issues, this article proposes a unified FSOD framework based on a prototype-conditioned GAN (P-GAN). The framework integrates three components to enhance robustness from data, feature, and label perspectives. First, dynamic augmented balanced sampling (DABS) is introduced to mitigate overfitting by applying diverse, adaptive augmentations to oversampled novel-class instances, improving both numerical balance and visual diversity. Second, to alleviate feature scarcity, a method is designed to synthesize region-of-interest features. Guided by prototype vectors and a cross-attention mechanism, P-GAN helps expand the feature space and alleviate classifier bias toward base classes. Third, to tackle the false negatives caused by missing annotations, a dynamic prototype-aware label corrector (DPLC) exploits a teacher–student architecture and prototype similarity to adaptively recalibrate labels and loss weights. Experiments on the DIOR and NWPU VHR-10.v2 benchmarks show that the proposed approach improves detection performance over the compared methods across multiple shot settings by mitigating classifier bias and refining feature representations.