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 …

This paper studies task adaptive pre-trained model selection, an underexplored problem of
assessing pre-trained models for the target task and select best ones from the model …

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 propose real-time, six degrees of freedom (6DoF), 3D face pose estimation without face
detection or landmark localization. We observe that estimating the 6DoF rigid transformation …

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 …

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 …

Contrastive visual pretraining based on the instance discrimination pretext task has made
significant progress. Notably, recent work on unsupervised pretraining has shown to surpass …

The notion of task similarity is at the core of various machine learning paradigms, such as
domain adaptation and meta-learning. Current methods to quantify it are often heuristic …

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