Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wan, Zhijing, Wang, Zhixiang, Wang, Zheng, Xu, Xin, Satoh, Shin'ichi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912452694769664
author Wan, Zhijing
Wang, Zhixiang
Wang, Zheng
Xu, Xin
Satoh, Shin'ichi
author_facet Wan, Zhijing
Wang, Zhixiang
Wang, Zheng
Xu, Xin
Satoh, Shin'ichi
contents One-shot subset selection serves as an effective tool to reduce deep learning training costs by identifying an informative data subset based on the information extracted by an information extractor (IE). Traditional IEs, typically pre-trained on the target dataset, are inherently dataset-dependent. Foundation models (FMs) offer a promising alternative, potentially mitigating this limitation. This work investigates two key questions: (1) Can FM-based subset selection outperform traditional IE-based methods across diverse datasets? (2) Do all FMs perform equally well as IEs for subset selection? Extensive experiments uncovered surprising insights: FMs consistently outperform traditional IEs on fine-grained datasets, whereas their advantage diminishes on coarse-grained datasets with noisy labels. Motivated by these finding, we propose RAM-APL (RAnking Mean-Accuracy of Pseudo-class Labels), a method tailored for fine-grained image datasets. RAM-APL leverages multiple FMs to enhance subset selection by exploiting their complementary strengths. Our approach achieves state-of-the-art performance on fine-grained datasets, including Oxford-IIIT Pet, Food-101, and Caltech-UCSD Birds-200-2011.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14473
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection
Wan, Zhijing
Wang, Zhixiang
Wang, Zheng
Xu, Xin
Satoh, Shin'ichi
Computer Vision and Pattern Recognition
Machine Learning
One-shot subset selection serves as an effective tool to reduce deep learning training costs by identifying an informative data subset based on the information extracted by an information extractor (IE). Traditional IEs, typically pre-trained on the target dataset, are inherently dataset-dependent. Foundation models (FMs) offer a promising alternative, potentially mitigating this limitation. This work investigates two key questions: (1) Can FM-based subset selection outperform traditional IE-based methods across diverse datasets? (2) Do all FMs perform equally well as IEs for subset selection? Extensive experiments uncovered surprising insights: FMs consistently outperform traditional IEs on fine-grained datasets, whereas their advantage diminishes on coarse-grained datasets with noisy labels. Motivated by these finding, we propose RAM-APL (RAnking Mean-Accuracy of Pseudo-class Labels), a method tailored for fine-grained image datasets. RAM-APL leverages multiple FMs to enhance subset selection by exploiting their complementary strengths. Our approach achieves state-of-the-art performance on fine-grained datasets, including Oxford-IIIT Pet, Food-101, and Caltech-UCSD Birds-200-2011.
title Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2506.14473