Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shao, Shitong, Yin, Zeyuan, Zhou, Muxin, Zhang, Xindong, Shen, Zhiqiang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917616047620096
author Shao, Shitong
Yin, Zeyuan
Zhou, Muxin
Zhang, Xindong
Shen, Zhiqiang
author_facet Shao, Shitong
Yin, Zeyuan
Zhou, Muxin
Zhang, Xindong
Shen, Zhiqiang
contents The lightweight "local-match-global" matching introduced by SRe2L successfully creates a distilled dataset with comprehensive information on the full 224x224 ImageNet-1k. However, this one-sided approach is limited to a particular backbone, layer, and statistics, which limits the improvement of the generalization of a distilled dataset. We suggest that sufficient and various "local-match-global" matching are more precise and effective than a single one and has the ability to create a distilled dataset with richer information and better generalization. We call this perspective "generalized matching" and propose Generalized Various Backbone and Statistical Matching (G-VBSM) in this work, which aims to create a synthetic dataset with densities, ensuring consistency with the complete dataset across various backbones, layers, and statistics. As experimentally demonstrated, G-VBSM is the first algorithm to obtain strong performance across both small-scale and large-scale datasets. Specifically, G-VBSM achieves a performance of 38.7% on CIFAR-100 with 128-width ConvNet, 47.6% on Tiny-ImageNet with ResNet18, and 31.4% on the full 224x224 ImageNet-1k with ResNet18, under images per class (IPC) 10, 50, and 10, respectively. These results surpass all SOTA methods by margins of 3.9%, 6.5%, and 10.1%, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2311_17950
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching
Shao, Shitong
Yin, Zeyuan
Zhou, Muxin
Zhang, Xindong
Shen, Zhiqiang
Computer Vision and Pattern Recognition
Artificial Intelligence
The lightweight "local-match-global" matching introduced by SRe2L successfully creates a distilled dataset with comprehensive information on the full 224x224 ImageNet-1k. However, this one-sided approach is limited to a particular backbone, layer, and statistics, which limits the improvement of the generalization of a distilled dataset. We suggest that sufficient and various "local-match-global" matching are more precise and effective than a single one and has the ability to create a distilled dataset with richer information and better generalization. We call this perspective "generalized matching" and propose Generalized Various Backbone and Statistical Matching (G-VBSM) in this work, which aims to create a synthetic dataset with densities, ensuring consistency with the complete dataset across various backbones, layers, and statistics. As experimentally demonstrated, G-VBSM is the first algorithm to obtain strong performance across both small-scale and large-scale datasets. Specifically, G-VBSM achieves a performance of 38.7% on CIFAR-100 with 128-width ConvNet, 47.6% on Tiny-ImageNet with ResNet18, and 31.4% on the full 224x224 ImageNet-1k with ResNet18, under images per class (IPC) 10, 50, and 10, respectively. These results surpass all SOTA methods by margins of 3.9%, 6.5%, and 10.1%, respectively.
title Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2311.17950