Transfer learning has been recently popularized as a data-efficient alternative to training models from scratch, in particular for computer vision tasks where it provides a remarkably solid baseline. The emergence of rich model repositories, such as TensorFlow Hub, enables the practitioners and researchers to unleash the potential of these models across a wide range of downstream tasks. As these repositories keep growing exponentially, efficiently selecting a good model for the task at hand becomes paramount. We provide a formalization of this problem through a familiar notion of regret and introduce the predominant strategies, namely task-agnostic (e.g. ranking models by their ImageNet performance) and task-aware search strategies (such as linear or kNN evaluation). We conduct a large-scale empirical study and show that both task-agnostic and task-aware methods can yield high regret. We then propose a simple and computationally efficient hybrid search strategy which outperforms the existing approaches. We highlight the practical benefits of the proposed solution on a set of 19 diverse vision tasks.
翻译:最近,转移学习作为一种数据效率高的培训模式从头开始被推广为一种数据效率高的替代方法,特别是在计算机愿景任务提供非常可靠的基准的计算机愿景任务方面。诸如TensorFlow 枢纽等丰富的模型库的出现,使实践者和研究人员能够在一系列广泛的下游任务中释放这些模型的潜力。随着这些数据库的迅速增长,高效率地为手头的任务选择一个良好的模式变得至关重要。我们通过一种熟悉的遗憾概念来正式解决这一问题,并引入主要战略,即任务不可知性(例如按其图像网络的性能排序模型)和任务可知性搜索战略(如线性或KNN),我们进行了大规模的实证研究,并表明任务不可知性和任务认知性方法都能产生极大的遗憾。我们随后提出了一种简单和计算高效的混合搜索战略,它比现有的方法要差。我们强调拟议的解决方案对一套19项不同愿景任务的实际好处。