The impressive performances of deep learning architectures is associated to massive increase of models complexity. Millions of parameters need be tuned, with training and inference time scaling accordingly. But is massive fine-tuning necessary? In this paper, focusing on image classification, we consider a simple transfer learning approach exploiting pretrained convolutional features as input for a fast kernel method. We refer to this approach as top-tuning, since only the kernel classifier is trained. By performing more than 2500 training processes we show that this top-tuning approach provides comparable accuracy w.r.t. fine-tuning, with a training time that is between one and two orders of magnitude smaller. These results suggest that top-tuning provides a useful alternative to fine-tuning in small/medium datasets, especially when training efficiency is crucial.

翻译：深度学习架构的卓越性能伴随着模型复杂度的急剧增加。数百万参数需要调整，训练和推理时间也随之增长。但大规模微调是否必要？本文以图像分类为研究对象，提出一种简单的迁移学习方法，该法将预训练的卷积特征作为快速核方法的输入。我们将此方法称为"顶层调优"，因为仅需训练核分类器。通过实施超过2500次训练过程，我们证明这种"顶层调优"方法在精度上可与微调相媲美，而训练时间却少一至两个数量级。这些结果表明，在中小规模数据集上，尤其是在训练效率至关重要的场景中，"顶层调优"可为微调提供一种极具价值的替代方案。