论文标题
使用精制对比度学习的几个射击对象检测
Few-shot Object Detection with Refined Contrastive Learning
论文作者
论文摘要
由于现实中抽样数据的稀缺性，很少有射击对象检测（FSOD）引起了越来越多的关注，因为它能够快速使用较少的数据来快速训练新的检测概念。但是，由于难以区分混乱的类别，仍然存在故障识别。我们还注意到，平均精度的高标准偏差揭示了不一致的检测性能。为此，我们提出了一种具有精致对比学习（FSRC）的新型FSOD方法。引入了预先确定的组件，以找出包含混乱类的新颖类中的相似之处。之后，在这组类别上明确执行了精致的对比学习（RCL），以增加它们之间的阶层距离。同时，检测结果更均匀地分布，从而进一步提高了性能。基于Pascal VOC和可可数据集的实验结果表明，我们提出的方法的表现优于当前的最新研究。
Due to the scarcity of sampling data in reality, few-shot object detection (FSOD) has drawn more and more attention because of its ability to quickly train new detection concepts with less data. However, there are still failure identifications due to the difficulty in distinguishing confusable classes. We also notice that the high standard deviation of average precision reveals the inconsistent detection performance. To this end, we propose a novel FSOD method with Refined Contrastive Learning (FSRC). A pre-determination component is introduced to find out the Resemblance Group from novel classes which contains confusable classes. Afterwards, Refined Contrastive Learning (RCL) is pointedly performed on this group of classes in order to increase the inter-class distances among them. In the meantime, the detection results distribute more uniformly which further improve the performance. Experimental results based on PASCAL VOC and COCO datasets demonstrate our proposed method outperforms the current state-of-the-art research.
