paper-with-me

Papers

DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning

2022-04-18 · Chengcheng Guo, Bo Zhao, Yanbing Bai

Coreset selection, which aims to select a subset of the most informative training samples, is a long-standing learning problem that can benefit many downstream tasks such as data-efficient learning, continual learning, neural architecture search, active learning, etc. However, many existing coreset selection methods are not designed for deep learning, which may have high complexity and poor generalization performance. In addition, the recently proposed methods are evaluated on models, datasets, and settings of different complexities. To advance the research of coreset selection in deep learning, we contribute a comprehensive code library, namely DeepCore, and provide an empirical study on popular coreset selection methods on CIFAR10 and ImageNet datasets. Extensive experiments on CIFAR10 and ImageNet datasets verify that, although various methods have advantages in certain experiment settings, random selection is still a strong baseline.

📄 PDF Abstract BibTeX arXiv:2204.08499

Code (1)

patrickzh/deepcore 공식 구현 pytorch

Tasks

Active LearningContinual LearningDeep LearningNeural Architecture Search

Similar Papers 제목 키워드 기반

2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore

2023-07-31 · J. H. Peterson, M. Prado Rodriguez, K. Hanson

IceCube DeepCore is an extension of the IceCube Neutrino Observatory designed to measure GeV scale atmospheric neutrino interactions for the purpose of neutrino oscillation studies. Distinguishing muon neutrinos from oth…

The Impact of Coreset Selection on Spurious Correlations and Group Robustness

2025-07-15 · Amaya Dharmasiri, William Yang, Polina Kirichenko, Lydia Liu 외 arxiv

Coreset selection methods have shown promise in reducing the training data size while maintaining model performance for data-efficient machine learning. However, as many datasets suffer from biases that cause models to l…

Non-Uniform Class-Wise Coreset Selection: Characterizing Category Difficulty for Data-Efficient Transfer Learning

2025-04-17 · Hanyu Zhang, Zhen Xing, Wenxuan Yang, Chenxi Ma 외

As transfer learning models and datasets grow larger, efficient adaptation and storage optimization have become critical needs. Coreset selection addresses these challenges by identifying and retaining the most informati…

Computational EfficiencyTransfer Learning

DeepCore: Simple Fingerprint Construction for Differentiating Homologous and Piracy Models

2024-11-01 · Haifeng Sun, Lan Zhang, Xiang-Yang Li

As intellectual property rights, the copyright protection of deep models is becoming increasingly important. Existing work has made many attempts at model watermarking and fingerprinting, but they have ignored homologous…

Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints

2023-11-15 · Xiaobo Xia, Jiale Liu, Shaokun Zhang, Qingyun Wu 외

Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms. It strives to identify a small subset from large-scale data, so that training only on the subse…