In this paper, we explore a novel knowledge-transfer task, termed as Deep Model
Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous …

Justifiably, while big data is the primary interest of research and public discourse, it is
essential to acknowledge that small data remains prevalent. The same technological and …

Transfer learning (TL) utilizes data or knowledge from one or more source domains to
facilitate learning in a target domain. It is particularly useful when the target domain has very …

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 …

We introduce a new measure to evaluate the transferability of representations learned by
classifiers. Our measure, the Log Expected Empirical Prediction (LEEP), is simple and easy …

Transfer learning has become a popular method for leveraging pre-trained models in
computer vision. However, without performing computationally expensive fine-tuning, it is …

Abstract Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative
for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only …

Artificial Intelligence of Things (AIoT) is an emerging frontier based on the deep fusion of
Internet of Things (IoT) and Artificial Intelligence (AI) technologies. The fundamental goal of …

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 …

Transfer learning across heterogeneous data distributions (aka domains) and distinct tasks
is a more general and challenging problem than conventional transfer learning, where either …