Transfer learning aims to make the most of existing pre-trained models to achieve better performance on a new task in limited data scenarios. However, it is unclear which models will perform best on which task, and it is prohibitively expensive to try all possible combinations. If transferability estimation offers a computation-efficient approach to evaluate the generalisation ability of models, prior works focused exclusively on classification settings. To overcome this limitation, we extend transferability metrics to object detection. We design a simple method to extract local features corresponding to each object within an image using ROI-Align. We also introduce TLogME, a transferability metric taking into account the coordinates regression task. In our experiments, we compare TLogME to state-of-the-art metrics in the estimation of transfer performance of the Faster-RCNN object detector. We evaluate all metrics on source and target selection tasks, for real and synthetic datasets, and with different backbone architectures. We show that, over different tasks, TLogME using the local extraction method provides a robust correlation with transfer performance and outperforms other transferability metrics on local and global level features.

翻译：迁移学习旨在充分利用已有的预训练模型，从而在有限数据场景下提升新任务的性能。然而，尚不清楚哪些模型对哪些任务表现最佳，且尝试所有可能的组合代价高昂。尽管可迁移性评估提供了一种计算高效的方法来评估模型的泛化能力，但以往的工作仅专注于分类设置。为克服这一局限，我们将可迁移性度量扩展到目标检测领域。我们设计了一种简单的方法，利用ROI-Align提取图像中每个物体对应的局部特征。同时，我们引入了TLogME，一种考虑坐标回归任务的可迁移性度量。在实验中，我们将TLogME与最新度量方法进行比较，用于评估Faster-RCNN目标检测器的迁移性能。我们在源任务与目标任务选择任务上，针对真实与合成数据集，以及不同骨干网络架构，对所有度量方法进行了评估。结果表明，在不同任务上，采用局部特征提取方法的TLogME与迁移性能之间表现出稳健的相关性，并在局部与全局层面特征上优于其他可迁移性度量方法。