【论文笔记】Frustratingly Simple Few-Shot Object Detection
摘要
小样本目标检测是新涌现的一个问题,先前的研究中表明元学习是一种非常有效的方法,而微调技术很少被人注意到,本文作者发现仅微调稀有类别上现有检测器的最后一层对于小样本目标检测任务至关重要。这种简单的方法在当前基准上比元学习方法高出大约 2~20 个百分点,有时甚至是先前方法的准确性的两倍。然而,少数样本的高方差往往会导致现有基准的不可靠性。作者在实验中使用微调方法用与其他方法进行对比实验,并且提出一种新的评估方法。
方法
In this work, we propose improved methods to evaluate few-shot object detection. We carefully examine fine-tuning based approaches, which are considered to be under-performing in the previous works . We focus on the training schedule and the instance-level feature normalization of the object detectors in model design and training based on fine-tuning.
在以往的研究中微调的方法被认为表现不佳,本文中在基于微调的模型设计和训练中重点关注了目标检测器的训练计划和实例级特征归一化的问题。
In all these works, fine-tuning based approaches are con