Skip to content
GCC AI Research

On Transferability of Machine Learning Models

MBZUAI · Notable

Research NLP CV Ethics Domain Adaptation

Summary

This article discusses domain shift in machine learning, where testing data differs from training data, and methods to mitigate it via domain adaptation and generalization. Domain adaptation uses labeled source data and unlabeled target data. Domain generalization uses labeled data from single or multiple source domains to generalize to unseen target domains. Why it matters: Research in mitigating domain shift enhances the robustness and applicability of AI models in diverse real-world scenarios.

Keywords

domain shift · machine learning · domain adaptation · domain generalization · MBZUAI

Read original article →

Get the weekly digest

Top AI stories from the GCC region, every week.

Related

Optimization of Module Transferability in Single Image Super-Resolution: Universality Assessment and Cycle Residual Blocks

arXiv ·

This paper introduces a method for quantifying the transferability of architectural components in Single Image Super-Resolution (SISR) models, termed "Universality," and proposes a Universality Assessment Equation (UAE). Guided by the UAE, the authors design optimized modules, Cycle Residual Block (CRB) and Depth-Wise Cycle Residual Block (DCRB), and demonstrate their effectiveness across various datasets and low-level tasks. Results show that networks using these modules outperform state-of-the-art methods, achieving improved PSNR or parameter reduction.