论文标题
afd-net：用于几个弹射对象检测的自适应完全偶联网络
AFD-Net: Adaptive Fully-Dual Network for Few-Shot Object Detection
论文作者
论文摘要
很少有射击对象检测（FSOD）旨在学习一个可以快速适应以前看不见的对象的检测器，这是具有挑战性和苛刻的示例。现有方法通过在检测器中使用共享组件（例如ROI头）执行分类和本地化的子任务来解决此问题，但很少有人将两个子任务的独特偏好用于考虑特征嵌入。在本文中，我们仔细分析了FSOD的特征，并介绍了一般的几杆检测器应考虑两个子任务的显式分解，并利用了两个子任务以增强特征表示。到最后，我们提出了一个简单而有效的自适应完全双重网络（AFD-NET）。具体来说，我们通过引入双重查询编码器和双重注意生成器来扩展R-CNN，以进行单独的特征提取器，以及用于单独的模型重新恢复的双聚合器。自发地，R-CNN检测器实现了单独的状态估计。此外，为了获取增强的特征表示，我们进一步引入了自适应融合机制，以在不同的子任务中适应性地进行特征融合。在各种环境中，对Pascal VOC和MS Coco的广泛实验表明，我们的方法通过很大的边距实现了新的最先进的性能，这表明了其有效性和泛化能力。
Few-shot object detection (FSOD) aims at learning a detector that can fast adapt to previously unseen objects with scarce annotated examples, which is challenging and demanding. Existing methods solve this problem by performing subtasks of classification and localization utilizing a shared component (e.g., RoI head) in the detector, yet few of them take the distinct preferences of two subtasks towards feature embedding into consideration. In this paper, we carefully analyze the characteristics of FSOD, and present that a general few-shot detector should consider the explicit decomposition of two subtasks, as well as leveraging information from both of them to enhance feature representations. To the end, we propose a simple yet effective Adaptive Fully-Dual Network (AFD-Net). Specifically, we extend Faster R-CNN by introducing Dual Query Encoder and Dual Attention Generator for separate feature extraction, and Dual Aggregator for separate model reweighting. Spontaneously, separate state estimation is achieved by the R-CNN detector. Besides, for the acquisition of enhanced feature representations, we further introduce Adaptive Fusion Mechanism to adaptively perform feature fusion in different subtasks. Extensive experiments on PASCAL VOC and MS COCO in various settings show that, our method achieves new state-of-the-art performance by a large margin, demonstrating its effectiveness and generalization ability.
