Leep: A new measure to evaluate transferability of learned representations

C Nguyen, T Hassner, M Seeger… - International …, 2020 - proceedings.mlr.press
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 …

[HTML][HTML] Wasserstein task embedding for measuring task similarities

X Liu, Y Bai, Y Lu, A Soltoggio, S Kolouri - Neural Networks, 2025 - Elsevier
Measuring similarities between different tasks is critical in a broad spectrum of machine
learning problems, including transfer, multi-task, continual, and meta-learning. Most current …

Feature-based distant domain transfer learning

S Niu, Y Hu, J Wang, Y Liu… - 2020 IEEE International …, 2020 - ieeexplore.ieee.org
In this paper, we study a not well-investigated but important transfer learning problem
termed Distant Domain Transfer Learning (DDTL). This topic is closely related to negative …

Cross-modality transfer learning for image-text information management

S Niu, Y Jiang, B Chen, J Wang, Y Liu… - ACM Transactions on …, 2021 - dl.acm.org
In the past decades, information from all kinds of data has been on a rapid increase. With
state-of-the-art performance, machine learning algorithms have been beneficial for …

Which model to transfer? finding the needle in the growing haystack

C Renggli, AS Pinto, L Rimanic… - Proceedings of the …, 2022 - openaccess.thecvf.com
Transfer learning has been recently popularized as a data-efficient alternative to training
models from scratch, in particular for computer vision tasks where it provides a remarkably …

[HTML][HTML] Assessing the Value of Transfer Learning Metrics for Radio Frequency Domain Adaptation

LJ Wong, BP Muller, S McPherson… - Machine Learning and …, 2024 - mdpi.com
The use of transfer learning (TL) techniques has become common practice in fields such as
computer vision (CV) and natural language processing (NLP). Leveraging prior knowledge …

Assessing the value of transfer learning metrics for RF domain adaptation

LJ Wong, S McPherson, AJ Michaels - arxiv preprint arxiv:2206.08329, 2022 - arxiv.org
The use of transfer learning (TL) techniques has become common practice in fields such as
computer vision (CV) and natural language processing (NLP). Leveraging prior knowledge …

A partition-based similarity for classification distributions

HS Helm, RD Mehta, B Duderstadt, W Yang… - arxiv preprint arxiv …, 2020 - arxiv.org
Herein we define a measure of similarity between classification distributions that is both
principled from the perspective of statistical pattern recognition and useful from the …

Task Fingerprinting for Meta Learning inBiomedical Image Analysis

P Godau, L Maier-Hein - … , Strasbourg, France, September 27–October 1 …, 2021 - Springer
Shortage of annotated data is one of the greatest bottlenecks in biomedical image analysis.
Meta learning studies how learning systems can increase in efficiency through experience …

Toward a Human-in-the-Loop Approach to Create Training Datasets for RDF Lexicalisation

JA Barbato, M Cremaschi, A Rula… - Proceedings of SAI …, 2023 - Springer
Datasets that include alignments between natural language and Knowledge Graphs are
fundamental to a wide variety of Natural Language Processing and Generation tasks …