Few-shot object detection (FSOD), which aims at learning a generic detector that can adapt to unseen tasks with scarce training samples, has witnessed consistent improvement recently. However, most existing methods ignore the efficiency issues, e.g., high computational complexity and slow adaptation speed. Notably, efficiency has become an increasingly important evaluation metric for few-shot techniques due to an emerging trend toward embedded AI. To this end, we present an efficient pretrain-transfer framework (PTF) baseline with no computational increment, which achieves comparable results with previous state-of-the-art (SOTA) methods. Upon this baseline, we devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed. Within the KI initializer, we propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights. Finally, our approach not only achieves the SOTA results across three public benchmarks, i.e., PASCAL VOC, COCO and LVIS, but also exhibits high efficiency with 1.8-100x faster adaptation speed against the other methods on COCO/LVIS benchmark during few-shot transfer. To our best knowledge, this is the first work to consider the efficiency problem in FSOD. We hope to motivate a trend toward powerful yet efficient few-shot technique development. The codes are publicly available at https://github.com/Ze-Yang/Efficient-FSOD.
翻译:少见的物体探测(FSOD)旨在学习一种能够适应培训样本稀少的无形任务的一般检测器(FSOD),但最近不断有改进;然而,大多数现有方法忽视了效率问题,例如计算复杂程度高和适应速度慢等;值得注意的是,由于正在出现嵌入AI的趋势,效率已成为对少见技术越来越重要的评价指标;为此,我们提出了一个高效的部署前转移框架(PTF)基线,没有计算递增,这与以前的先进技术(SOTA)方法取得了类似的结果。在此基线上,我们设计了一个名为知识继承(KI)的初始化器,以可靠地初始化箱分类器的新重量,从而有效地便利知识转移进程,提高适应速度。在KIAFA初始化器中,我们提出了调整长度调整战略的战略,以缓解预测的新重量与预测的基础重量之间的矢量不一致。最后,我们的方法不仅在三个公共基准基准(即PASAL VOC、CO-CO-SO-CO-SD)之间取得了类似的结果,而且在18-I-S-S-C-S-S-S-C-C-C-SLSDDS-S-S-S-S-S-C-C-C-SOL-SV-SOL-SOL-S-S-S-S-S-SD-S-SD-S-S-SOL-S-S-S-S-S-S-S-S-S-S-S-SOL-SOL-I-I-SD-SD-SD-I-SFAR-I-I-I-S-S-I-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-SFAR-S-S-S-S-I-I-I-I-SDFAR-SOL-SDFAR-SDFA-SDFM-I-I-I-I-I-I-S-S-S-SDFS-S-S-S-SFA-S-S-S-S-S-S-S-S-S-S-