ECEA:用于少样本目标检测的可扩展共存注意力
ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection
AI总结:
针对少样本目标检测中因训练样本仅含局部区域导致无法检测完整目标的问题,提出可扩展共存注意力(ECEA)模块,通过在不同特征尺度上从局部扩展至共存区域来推断全局目标,在PASCAL VOC和COCO上取得了新的最优性能。
摘要:
少样本目标检测(FSOD)旨在从极少的标注样本中识别目标。近期,大多数现有的FSOD方法采用两阶段学习范式,通过学习全局特征,将丰富基类上学到的知识迁移以辅助少样本检测器。然而,这些方法很少考虑目标从局部到全局的定位。受限于FSOD中训练数据的稀缺性,新类的训练样本通常只捕捉到目标的部分区域,导致此类方法在测试期间无法检测到完全未见过的目标。为解决此问题,我们提出了一种可扩展共存注意力(ECEA)模块,使模型能够根据局部区域推断全局目标。本质上,该模块在样本充足的基类阶段持续学习可扩展能力,并将其迁移至新类阶段,从而辅助少样本模型快速适应将局部区域扩展至共存区域的过程。具体而言,我们首先设计了一种可扩展注意力机制,它从一个局部区域出发,将注意力扩展至与给定局部区域相似且相邻的共存区域。随后,我们在不同的特征尺度上实现该可扩展注意力机制,以在各种感受野中逐步发现完整目标。在PASCAL VOC和COCO数据集上的大量实验表明,尽管部分区域未出现在训练样本中,我们的ECEA模块仍能辅助少样本检测器完整预测目标,并与现有FSOD方法相比取得了新的最优性能。
英文摘要:
Few-shot object detection (FSOD) identifies objects from extremely few annotated samples. Most existing FSOD methods, recently, apply the two-stage learning paradigm, which transfers the knowledge learned from abundant base classes to assist the few-shot detectors by learning the global features. However, such existing FSOD approaches seldom consider the localization of objects from local to global. Limited by the scarce training data in FSOD, the training samples of novel classes typically capture part of objects, resulting in such FSOD methods cannot detect the completely unseen object during testing. To tackle this problem, we propose an Extensible Co-Existing Attention (ECEA) module to enable the model to infer the global object according to the local parts. Essentially, the proposed module continuously learns the extensible ability on the base stage with abundant samples and transfers it to the novel stage, which can assist the few-shot model to quickly adapt in extending local regions to co-existing regions. Specifically, we first devise an extensible attention mechanism that starts with a local region and extends attention to co-existing regions that are similar and adjacent to the given local region. We then implement the extensible attention mechanism in different feature scales to progressively discover the full object in various receptive fields. Extensive experiments on the PASCAL VOC and COCO datasets show that our ECEA module can assist the few-shot detector to completely predict the object despite some regions failing to appear in the training samples and achieve the new state of the art compared with existing FSOD methods.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。