Few-shot object detection, the problem of modelling novel object detection categories with few training instances, is an emerging topic in the area of few-shot learning and object detection. Contemporary techniques can be divided into two groups: fine-tuning based and meta-learning based approaches. While meta-learning approaches aim to learn dedicated meta-models for mapping samples to novel class models, fine-tuning approaches tackle few-shot detection in a simpler manner, by adapting the detection model to novel classes through gradient based optimization. Despite their simplicity, fine-tuning based approaches typically yield competitive detection results. Based on this observation, we focus on the role of loss functions and augmentations as the force driving the fine-tuning process, and propose to tune their dynamics through meta-learning principles. The proposed training scheme, therefore, allows learning inductive biases that can boost few-shot detection, while keeping the advantages of fine-tuning based approaches. In addition, the proposed approach yields interpretable loss functions, as opposed to highly parametric and complex few-shot meta-models. The experimental results highlight the merits of the proposed scheme, with significant improvements over the strong fine-tuning based few-shot detection baselines on benchmark Pascal VOC and MS-COCO datasets, in terms of both standard and generalized few-shot performance metrics.

翻译：小样本目标检测（Few-shot Object Detection）指在仅有少量训练样本的情况下建模新目标检测类别的任务，是小样本学习与目标检测领域的新兴课题。现有技术可分为两类：基于微调的方法和基于元学习的方法。元学习方法旨在学习专用元模型，以将样本映射至新类别模型；而微调方法则通过梯度优化将检测模型适应至新类别，以更简洁的方式处理小样本检测。尽管方法简单，基于微调的方法通常能取得有竞争力的检测结果。基于此观察，本文聚焦于驱动微调过程的损失函数与数据增强的作用，并提出通过元学习原理调谐其动态机制。所提出的训练方案允许学习能提升小样本检测的归纳偏置，同时保留基于微调方法的优势。此外，该方法能产生可解释的损失函数，与高度参数化且复杂的小样本元模型形成对比。实验结果表明了该方案的优越性，在标准Pascal VOC与MS-COCO基准数据集上，相较于强力的基于微调的小样本检测基线方法，在标准与泛化小样本性能指标上均实现了显著提升。