Detecting rare objects from a few examples is an emerging problem. Prior works show meta-learning is a promising approach. But, fine-tuning techniques have drawn scant attention. We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods. However, the high variance in the few samples often leads to the unreliability of existing benchmarks. We revise the evaluation protocols by sampling multiple groups of training examples to obtain stable comparisons and build new benchmarks based on three datasets: PASCAL VOC, COCO and LVIS. Again, our fine-tuning approach establishes a new state of the art on the revised benchmarks. The code as well as the pretrained models are available at https://github.com/ucbdrive/few-shot-object-detection.

翻译：从几个例子中探测稀有物体是一个新出现的问题。 先前的工程显示,元学习是一种很有希望的方法。 但是,微调技术很少引起注意。 我们发现,微调仅对稀有类别现有探测器的最后一层进行微调,对于微小的天体探测任务至关重要。 这种简单的方法比元学习方法在目前基准上高出大约2~20个百分点,有时甚至比以前方法的准确性高出一倍。然而,少数样本的高度差异往往导致现有基准的不可靠性。我们通过对多组培训实例进行抽样抽样检查来修订评价协议,以获得稳定的比较,并根据三个数据集(PACAL VOC、COCO和LVIS)建立新的基准。我们微调方法再次在订正基准上确立了新的艺术状态。 守则和预先培训的模式可在https://github.com/ucbdrive/few-shot-object-detraction上查阅。