# Top-Tuning: a study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods Source: [Top-Tuning: a study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:58:41.298Z Authors: Paolo Didier Alfano, Vito Paolo Pastore, Lorenzo Rosasco, Francesca Odone Published: 2022-09-16T13:46:59.000Z ## Abstract The impressive performance of deep learning architectures is associated with a massive increase in model complexity. Millions of parameters need to be tuned, with training and inference time scaling accordingly, together with energy consumption. But is massive fine-tuning always necessary? In this paper, focusing on image classification, we consider a simple transfer learning approach exploiting pre-trained convolutional features as input for a fast-to-train kernel method. We refer to this approach as \\textit{top-tuning} since only the kernel classifier is trained on the target dataset. In our study, we perform more than 3000 training processes focusing on 32 small to medium-sized target datasets, a typical situation where transfer learning is necessary. We show that the top-tuning approach provides comparable accuracy with respect to fine-tuning, with a training time between one and two orders of magnitude smaller. These results suggest that top-tuning is an effective alternative to fine-tuning in small/medium datasets, being especially useful when training time efficiency and computational resources saving are crucial. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()