This paper focuses on model transferability estimation, ie, assessing the performance of pre-
trained models on a downstream task without performing fine-tuning. Motivated by the …

Transfer learning has become crucial in computer vision tasks due to the vast availability of
pre-trained deep learning models. However, selecting the optimal pre-trained model from a …

This paper addresses the problem of ranking pre-trained models for object detection and
image classification. Selecting the best pre-trained model by fine-tuning is an expensive and …

Abstract Figuring out which Pre-Trained Model (PTM) from a model zoo fits the target task is
essential to take advantage of plentiful model resources. With the availability of numerous …

Transfer learning transfers the knowledge acquired by a model from a source task to
multiple downstream target tasks with minimal fine-tuning. The success of transfer learning …

This paper investigates an under-explored but important problem: given a collection of pre-
trained neural networks, predicting their performance on each multi-modal task without fine …

This paper investigates an under-explored but important problem: given a collection of pre-
trained neural networks, predicting their performance on each multi-modal task without fine …

Transferability estimation has been attached to great attention in the computer vision fields.
Researchers try to estimate with low computational cost the performance of a model when …

The remarkable success of" pretrain-then-finetune" paradigm has led to a proliferation of
available pre-trained models for vision tasks. This surge presents a significant challenge in …

As transfer learning techniques are increasingly used to transfer knowledge from the source
model to the target task it becomes important to quantify which source models are suitable …