Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.

<p>Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.<...

Full description

Saved in:
Bibliographic Details
Main Author: Yide Di (20969124) (author)
Other Authors: Yun Liao (160524) (author), Hao Zhou (136535) (author), Kaijun Zhu (18283913) (author), Qing Duan (541846) (author), Junhui Liu (2063140) (author), Mingyu Lu (2333083) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852021690906705920
author Yide Di (20969124)
author2 Yun Liao (160524)
Hao Zhou (136535)
Kaijun Zhu (18283913)
Qing Duan (541846)
Junhui Liu (2063140)
Mingyu Lu (2333083)
author2_role author
author
author
author
author
author
author_facet Yide Di (20969124)
Yun Liao (160524)
Hao Zhou (136535)
Kaijun Zhu (18283913)
Qing Duan (541846)
Junhui Liu (2063140)
Mingyu Lu (2333083)
author_role author
dc.creator.none.fl_str_mv Yide Di (20969124)
Yun Liao (160524)
Hao Zhou (136535)
Kaijun Zhu (18283913)
Qing Duan (541846)
Junhui Liu (2063140)
Mingyu Lu (2333083)
dc.date.none.fl_str_mv 2025-03-31T20:05:25Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0319051.g005
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Fine-tuning_on_same-model_feature_matching_tasks_The_X-FFN_and_Y-FFN_represent_the_assistants_of_any_two_kinds_of_pre-trained_different_modal_images_in_the_second_stage_of_Fig_4_The_fine-tuning_of_the_X-modal_image_and_the_fine-tuning_of_th/28701039
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Sociology
Science Policy
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
multimodal image applications
image feature matching
experimental results demonstrate
data augmentation algorithm
across different modals
ufm exhibits versatility
div >< p
imbalanced modal datasets
specific modals
specific datasets
sparse data
wide spectrum
ufm excels
ufm </
trained model
staged pre
remains challenging
modal images
foundational task
computer vision
dc.title.none.fl_str_mv Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p>Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.</p>
eu_rights_str_mv openAccess
id Manara_c85d9fb8fdf8167ec4cd16cad454e521
identifier_str_mv 10.1371/journal.pone.0319051.g005
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/28701039
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.Yide Di (20969124)Yun Liao (160524)Hao Zhou (136535)Kaijun Zhu (18283913)Qing Duan (541846)Junhui Liu (2063140)Mingyu Lu (2333083)SociologyScience PolicySpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedmultimodal image applicationsimage feature matchingexperimental results demonstratedata augmentation algorithmacross different modalsufm exhibits versatilitydiv >< pimbalanced modal datasetsspecific modalsspecific datasetssparse datawide spectrumufm excelsufm </trained modelstaged preremains challengingmodal imagesfoundational taskcomputer vision<p>Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.</p>2025-03-31T20:05:25ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0319051.g005https://figshare.com/articles/figure/Fine-tuning_on_same-model_feature_matching_tasks_The_X-FFN_and_Y-FFN_represent_the_assistants_of_any_two_kinds_of_pre-trained_different_modal_images_in_the_second_stage_of_Fig_4_The_fine-tuning_of_the_X-modal_image_and_the_fine-tuning_of_th/28701039CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/287010392025-03-31T20:05:25Z
spellingShingle Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.
Yide Di (20969124)
Sociology
Science Policy
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
multimodal image applications
image feature matching
experimental results demonstrate
data augmentation algorithm
across different modals
ufm exhibits versatility
div >< p
imbalanced modal datasets
specific modals
specific datasets
sparse data
wide spectrum
ufm excels
ufm </
trained model
staged pre
remains challenging
modal images
foundational task
computer vision
status_str publishedVersion
title Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.
title_full Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.
title_fullStr Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.
title_full_unstemmed Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.
title_short Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.
title_sort Fine-tuning on same-model feature matching tasks. The X-FFN and Y-FFN represent the assistants of any two kinds of pre-trained different modal images in the second stage of Fig 4. The fine-tuning of the X-modal image and the fine-tuning of the Y-modal image are independent of each other.
topic Sociology
Science Policy
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
multimodal image applications
image feature matching
experimental results demonstrate
data augmentation algorithm
across different modals
ufm exhibits versatility
div >< p
imbalanced modal datasets
specific modals
specific datasets
sparse data
wide spectrum
ufm excels
ufm </
trained model
staged pre
remains challenging
modal images
foundational task
computer vision