Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kim, Sungyeon, Kim, Donghyun, Kwak, Suha
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915108259627008
author Kim, Sungyeon
Kim, Donghyun
Kwak, Suha
author_facet Kim, Sungyeon
Kim, Donghyun
Kwak, Suha
contents A common practice in metric learning is to train and test an embedding model for each dataset. This dataset-specific approach fails to simulate real-world scenarios that involve multiple heterogeneous distributions of data. In this regard, we explore a new metric learning paradigm, called Unified Metric Learning (UML), which learns a unified distance metric capable of capturing relations across multiple data distributions. UML presents new challenges, such as imbalanced data distribution and bias towards dominant distributions. These issues cause standard metric learning methods to fail in learning a unified metric. To address these challenges, we propose Parameter-efficient Unified Metric leArning (PUMA), which consists of a pre-trained frozen model and two additional modules, stochastic adapter and prompt pool. These modules enable to capture dataset-specific knowledge while avoiding bias towards dominant distributions. Additionally, we compile a new unified metric learning benchmark with a total of 8 different datasets. PUMA outperforms the state-of-the-art dataset-specific models while using about 69 times fewer trainable parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2309_08944
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning
Kim, Sungyeon
Kim, Donghyun
Kwak, Suha
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
A common practice in metric learning is to train and test an embedding model for each dataset. This dataset-specific approach fails to simulate real-world scenarios that involve multiple heterogeneous distributions of data. In this regard, we explore a new metric learning paradigm, called Unified Metric Learning (UML), which learns a unified distance metric capable of capturing relations across multiple data distributions. UML presents new challenges, such as imbalanced data distribution and bias towards dominant distributions. These issues cause standard metric learning methods to fail in learning a unified metric. To address these challenges, we propose Parameter-efficient Unified Metric leArning (PUMA), which consists of a pre-trained frozen model and two additional modules, stochastic adapter and prompt pool. These modules enable to capture dataset-specific knowledge while avoiding bias towards dominant distributions. Additionally, we compile a new unified metric learning benchmark with a total of 8 different datasets. PUMA outperforms the state-of-the-art dataset-specific models while using about 69 times fewer trainable parameters.
title Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2309.08944