Which Model to Transfer? A Survey on Transferability Estimation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911782867566592 |
|---|---|
| author | Ding, Yuhe Jiang, Bo Yu, Aijing Zheng, Aihua Liang, Jian |
| author_facet | Ding, Yuhe Jiang, Bo Yu, Aijing Zheng, Aihua Liang, Jian |
| contents | Transfer learning methods endeavor to leverage relevant knowledge from existing source pre-trained models or datasets to solve downstream target tasks. With the increase in the scale and quantity of available pre-trained models nowadays, it becomes critical to assess in advance whether they are suitable for a specific target task. Model transferability estimation is an emerging and growing area of interest, aiming to propose a metric to quantify this suitability without training them individually, which is computationally prohibitive. Despite extensive recent advances already devoted to this area, they have custom terminological definitions and experimental settings. In this survey, we present the first review of existing advances in this area and categorize them into two separate realms: source-free model transferability estimation and source-dependent model transferability estimation. Each category is systematically defined, accompanied by a comprehensive taxonomy. Besides, we address challenges and outline future research directions, intending to provide a comprehensive guide to aid researchers and practitioners. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15231 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Which Model to Transfer? A Survey on Transferability Estimation Ding, Yuhe Jiang, Bo Yu, Aijing Zheng, Aihua Liang, Jian Machine Learning Computer Vision and Pattern Recognition Transfer learning methods endeavor to leverage relevant knowledge from existing source pre-trained models or datasets to solve downstream target tasks. With the increase in the scale and quantity of available pre-trained models nowadays, it becomes critical to assess in advance whether they are suitable for a specific target task. Model transferability estimation is an emerging and growing area of interest, aiming to propose a metric to quantify this suitability without training them individually, which is computationally prohibitive. Despite extensive recent advances already devoted to this area, they have custom terminological definitions and experimental settings. In this survey, we present the first review of existing advances in this area and categorize them into two separate realms: source-free model transferability estimation and source-dependent model transferability estimation. Each category is systematically defined, accompanied by a comprehensive taxonomy. Besides, we address challenges and outline future research directions, intending to provide a comprehensive guide to aid researchers and practitioners. |
| title | Which Model to Transfer? A Survey on Transferability Estimation |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.15231 |